{"current_steps": 1, "total_steps": 670, "loss": 0.057, "lr": 1.4925373134328358e-06, "epoch": 0.0074487895716946, "percentage": 0.15, "elapsed_time": "0:00:14", "remaining_time": "2:43:14"} {"current_steps": 2, "total_steps": 670, "loss": 0.0606, "lr": 2.9850746268656716e-06, "epoch": 0.0148975791433892, "percentage": 0.3, "elapsed_time": "0:00:28", "remaining_time": "2:36:12"} {"current_steps": 3, "total_steps": 670, "loss": 0.0588, "lr": 4.477611940298508e-06, "epoch": 0.0223463687150838, "percentage": 0.45, "elapsed_time": "0:00:40", "remaining_time": "2:29:55"} {"current_steps": 4, "total_steps": 670, "loss": 0.0584, "lr": 5.970149253731343e-06, "epoch": 0.0297951582867784, "percentage": 0.6, "elapsed_time": "0:00:53", "remaining_time": "2:29:14"} {"current_steps": 5, "total_steps": 670, "loss": 0.0578, "lr": 7.4626865671641785e-06, "epoch": 0.037243947858473, "percentage": 0.75, "elapsed_time": "0:01:07", "remaining_time": "2:29:36"} {"current_steps": 5, "total_steps": 670, "eval_loss": 0.05715847760438919, "epoch": 0.037243947858473, "percentage": 0.75, "elapsed_time": "0:01:08", "remaining_time": "2:32:44"} {"current_steps": 6, "total_steps": 670, "loss": 0.057, "lr": 8.955223880597016e-06, "epoch": 0.0446927374301676, "percentage": 0.9, "elapsed_time": "0:01:22", "remaining_time": "2:31:32"} {"current_steps": 7, "total_steps": 670, "loss": 0.0582, "lr": 1.0447761194029851e-05, "epoch": 0.0521415270018622, "percentage": 1.04, "elapsed_time": "0:01:34", "remaining_time": "2:29:33"} {"current_steps": 8, "total_steps": 670, "loss": 0.0557, "lr": 1.1940298507462686e-05, "epoch": 0.0595903165735568, "percentage": 1.19, "elapsed_time": "0:01:47", "remaining_time": "2:28:37"} {"current_steps": 9, "total_steps": 670, "loss": 0.054, "lr": 1.3432835820895523e-05, "epoch": 0.0670391061452514, "percentage": 1.34, "elapsed_time": "0:02:01", "remaining_time": "2:28:46"} {"current_steps": 10, "total_steps": 670, "loss": 0.0546, "lr": 1.4925373134328357e-05, "epoch": 0.074487895716946, "percentage": 1.49, "elapsed_time": "0:02:16", "remaining_time": "2:29:42"} {"current_steps": 10, "total_steps": 670, "eval_loss": 0.05712079629302025, "epoch": 0.074487895716946, "percentage": 1.49, "elapsed_time": "0:02:17", "remaining_time": "2:31:14"} {"current_steps": 11, "total_steps": 670, "loss": 0.0557, "lr": 1.6417910447761194e-05, "epoch": 0.08193668528864059, "percentage": 1.64, "elapsed_time": "0:02:31", "remaining_time": "2:30:54"} {"current_steps": 12, "total_steps": 670, "loss": 0.0574, "lr": 1.791044776119403e-05, "epoch": 0.0893854748603352, "percentage": 1.79, "elapsed_time": "0:02:44", "remaining_time": "2:30:05"} {"current_steps": 13, "total_steps": 670, "loss": 0.0576, "lr": 1.9402985074626868e-05, "epoch": 0.09683426443202979, "percentage": 1.94, "elapsed_time": "0:02:57", "remaining_time": "2:29:40"} {"current_steps": 14, "total_steps": 670, "loss": 0.0544, "lr": 2.0895522388059702e-05, "epoch": 0.1042830540037244, "percentage": 2.09, "elapsed_time": "0:03:10", "remaining_time": "2:28:56"} {"current_steps": 15, "total_steps": 670, "loss": 0.0544, "lr": 2.238805970149254e-05, "epoch": 0.11173184357541899, "percentage": 2.24, "elapsed_time": "0:03:22", "remaining_time": "2:27:33"} {"current_steps": 15, "total_steps": 670, "eval_loss": 0.05689356476068497, "epoch": 0.11173184357541899, "percentage": 2.24, "elapsed_time": "0:03:24", "remaining_time": "2:28:35"} {"current_steps": 16, "total_steps": 670, "loss": 0.0581, "lr": 2.3880597014925373e-05, "epoch": 0.1191806331471136, "percentage": 2.39, "elapsed_time": "0:03:37", "remaining_time": "2:28:03"} {"current_steps": 17, "total_steps": 670, "loss": 0.0553, "lr": 2.537313432835821e-05, "epoch": 0.1266294227188082, "percentage": 2.54, "elapsed_time": "0:03:50", "remaining_time": "2:27:53"} {"current_steps": 18, "total_steps": 670, "loss": 0.0525, "lr": 2.6865671641791047e-05, "epoch": 0.1340782122905028, "percentage": 2.69, "elapsed_time": "0:04:04", "remaining_time": "2:27:48"} {"current_steps": 19, "total_steps": 670, "loss": 0.0541, "lr": 2.835820895522388e-05, "epoch": 0.14152700186219738, "percentage": 2.84, "elapsed_time": "0:04:18", "remaining_time": "2:27:22"} {"current_steps": 20, "total_steps": 670, "loss": 0.0546, "lr": 2.9850746268656714e-05, "epoch": 0.148975791433892, "percentage": 2.99, "elapsed_time": "0:04:30", "remaining_time": "2:26:38"} {"current_steps": 20, "total_steps": 670, "eval_loss": 0.056141287088394165, "epoch": 0.148975791433892, "percentage": 2.99, "elapsed_time": "0:04:32", "remaining_time": "2:27:26"} {"current_steps": 21, "total_steps": 670, "loss": 0.0522, "lr": 3.1343283582089554e-05, "epoch": 0.1564245810055866, "percentage": 3.13, "elapsed_time": "0:04:46", "remaining_time": "2:27:20"} {"current_steps": 22, "total_steps": 670, "loss": 0.0537, "lr": 3.283582089552239e-05, "epoch": 0.16387337057728119, "percentage": 3.28, "elapsed_time": "0:05:00", "remaining_time": "2:27:24"} {"current_steps": 23, "total_steps": 670, "loss": 0.055, "lr": 3.432835820895522e-05, "epoch": 0.1713221601489758, "percentage": 3.43, "elapsed_time": "0:05:13", "remaining_time": "2:27:06"} {"current_steps": 24, "total_steps": 670, "loss": 0.0493, "lr": 3.582089552238806e-05, "epoch": 0.1787709497206704, "percentage": 3.58, "elapsed_time": "0:05:27", "remaining_time": "2:26:47"} {"current_steps": 25, "total_steps": 670, "loss": 0.0584, "lr": 3.73134328358209e-05, "epoch": 0.186219739292365, "percentage": 3.73, "elapsed_time": "0:05:40", "remaining_time": "2:26:27"} {"current_steps": 25, "total_steps": 670, "eval_loss": 0.054041195660829544, "epoch": 0.186219739292365, "percentage": 3.73, "elapsed_time": "0:05:41", "remaining_time": "2:27:03"} {"current_steps": 26, "total_steps": 670, "loss": 0.0498, "lr": 3.8805970149253736e-05, "epoch": 0.19366852886405958, "percentage": 3.88, "elapsed_time": "0:05:55", "remaining_time": "2:26:52"} {"current_steps": 27, "total_steps": 670, "loss": 0.0503, "lr": 4.029850746268657e-05, "epoch": 0.2011173184357542, "percentage": 4.03, "elapsed_time": "0:06:09", "remaining_time": "2:26:33"} {"current_steps": 28, "total_steps": 670, "loss": 0.0487, "lr": 4.1791044776119404e-05, "epoch": 0.2085661080074488, "percentage": 4.18, "elapsed_time": "0:06:22", "remaining_time": "2:25:59"} {"current_steps": 29, "total_steps": 670, "loss": 0.0527, "lr": 4.328358208955224e-05, "epoch": 0.21601489757914338, "percentage": 4.33, "elapsed_time": "0:06:34", "remaining_time": "2:25:23"} {"current_steps": 30, "total_steps": 670, "loss": 0.0461, "lr": 4.477611940298508e-05, "epoch": 0.22346368715083798, "percentage": 4.48, "elapsed_time": "0:06:48", "remaining_time": "2:25:19"} {"current_steps": 30, "total_steps": 670, "eval_loss": 0.050379376858472824, "epoch": 0.22346368715083798, "percentage": 4.48, "elapsed_time": "0:06:50", "remaining_time": "2:25:48"} {"current_steps": 31, "total_steps": 670, "loss": 0.0512, "lr": 4.626865671641791e-05, "epoch": 0.2309124767225326, "percentage": 4.63, "elapsed_time": "0:07:04", "remaining_time": "2:25:40"} {"current_steps": 32, "total_steps": 670, "loss": 0.0443, "lr": 4.7761194029850745e-05, "epoch": 0.2383612662942272, "percentage": 4.78, "elapsed_time": "0:07:17", "remaining_time": "2:25:12"} {"current_steps": 33, "total_steps": 670, "loss": 0.0464, "lr": 4.9253731343283586e-05, "epoch": 0.24581005586592178, "percentage": 4.93, "elapsed_time": "0:07:30", "remaining_time": "2:24:51"} {"current_steps": 34, "total_steps": 670, "loss": 0.0451, "lr": 5.074626865671642e-05, "epoch": 0.2532588454376164, "percentage": 5.07, "elapsed_time": "0:07:43", "remaining_time": "2:24:21"} {"current_steps": 35, "total_steps": 670, "loss": 0.0472, "lr": 5.223880597014925e-05, "epoch": 0.260707635009311, "percentage": 5.22, "elapsed_time": "0:07:55", "remaining_time": "2:23:47"} {"current_steps": 35, "total_steps": 670, "eval_loss": 0.04620573669672012, "epoch": 0.260707635009311, "percentage": 5.22, "elapsed_time": "0:07:56", "remaining_time": "2:24:13"} {"current_steps": 36, "total_steps": 670, "loss": 0.0418, "lr": 5.373134328358209e-05, "epoch": 0.2681564245810056, "percentage": 5.37, "elapsed_time": "0:08:10", "remaining_time": "2:24:00"} {"current_steps": 37, "total_steps": 670, "loss": 0.0439, "lr": 5.5223880597014934e-05, "epoch": 0.2756052141527002, "percentage": 5.52, "elapsed_time": "0:08:23", "remaining_time": "2:23:36"} {"current_steps": 38, "total_steps": 670, "loss": 0.0431, "lr": 5.671641791044776e-05, "epoch": 0.28305400372439476, "percentage": 5.67, "elapsed_time": "0:08:36", "remaining_time": "2:23:11"} {"current_steps": 39, "total_steps": 670, "loss": 0.0392, "lr": 5.82089552238806e-05, "epoch": 0.2905027932960894, "percentage": 5.82, "elapsed_time": "0:08:51", "remaining_time": "2:23:24"} {"current_steps": 40, "total_steps": 670, "loss": 0.0422, "lr": 5.970149253731343e-05, "epoch": 0.297951582867784, "percentage": 5.97, "elapsed_time": "0:09:05", "remaining_time": "2:23:07"} {"current_steps": 40, "total_steps": 670, "eval_loss": 0.043025754392147064, "epoch": 0.297951582867784, "percentage": 5.97, "elapsed_time": "0:09:06", "remaining_time": "2:23:31"} {"current_steps": 41, "total_steps": 670, "loss": 0.0382, "lr": 6.119402985074628e-05, "epoch": 0.3054003724394786, "percentage": 6.12, "elapsed_time": "0:09:20", "remaining_time": "2:23:21"} {"current_steps": 42, "total_steps": 670, "loss": 0.0381, "lr": 6.268656716417911e-05, "epoch": 0.3128491620111732, "percentage": 6.27, "elapsed_time": "0:09:33", "remaining_time": "2:22:53"} {"current_steps": 43, "total_steps": 670, "loss": 0.0423, "lr": 6.417910447761194e-05, "epoch": 0.3202979515828678, "percentage": 6.42, "elapsed_time": "0:09:47", "remaining_time": "2:22:48"} {"current_steps": 44, "total_steps": 670, "loss": 0.0426, "lr": 6.567164179104478e-05, "epoch": 0.32774674115456237, "percentage": 6.57, "elapsed_time": "0:10:00", "remaining_time": "2:22:19"} {"current_steps": 45, "total_steps": 670, "loss": 0.0354, "lr": 6.716417910447762e-05, "epoch": 0.33519553072625696, "percentage": 6.72, "elapsed_time": "0:10:13", "remaining_time": "2:22:00"} {"current_steps": 45, "total_steps": 670, "eval_loss": 0.04075229912996292, "epoch": 0.33519553072625696, "percentage": 6.72, "elapsed_time": "0:10:14", "remaining_time": "2:22:20"} {"current_steps": 46, "total_steps": 670, "loss": 0.0393, "lr": 6.865671641791044e-05, "epoch": 0.3426443202979516, "percentage": 6.87, "elapsed_time": "0:10:28", "remaining_time": "2:22:09"} {"current_steps": 47, "total_steps": 670, "loss": 0.0387, "lr": 7.014925373134329e-05, "epoch": 0.3500931098696462, "percentage": 7.01, "elapsed_time": "0:10:42", "remaining_time": "2:21:53"} {"current_steps": 48, "total_steps": 670, "loss": 0.0383, "lr": 7.164179104477612e-05, "epoch": 0.3575418994413408, "percentage": 7.16, "elapsed_time": "0:10:55", "remaining_time": "2:21:30"} {"current_steps": 49, "total_steps": 670, "loss": 0.0349, "lr": 7.313432835820896e-05, "epoch": 0.3649906890130354, "percentage": 7.31, "elapsed_time": "0:11:08", "remaining_time": "2:21:15"} {"current_steps": 50, "total_steps": 670, "loss": 0.038, "lr": 7.46268656716418e-05, "epoch": 0.37243947858473, "percentage": 7.46, "elapsed_time": "0:11:22", "remaining_time": "2:21:02"} {"current_steps": 50, "total_steps": 670, "eval_loss": 0.03857889771461487, "epoch": 0.37243947858473, "percentage": 7.46, "elapsed_time": "0:11:23", "remaining_time": "2:21:19"} {"current_steps": 51, "total_steps": 670, "loss": 0.0351, "lr": 7.611940298507463e-05, "epoch": 0.37988826815642457, "percentage": 7.61, "elapsed_time": "0:11:37", "remaining_time": "2:21:06"} {"current_steps": 52, "total_steps": 670, "loss": 0.035, "lr": 7.761194029850747e-05, "epoch": 0.38733705772811916, "percentage": 7.76, "elapsed_time": "0:11:50", "remaining_time": "2:20:41"} {"current_steps": 53, "total_steps": 670, "loss": 0.0349, "lr": 7.910447761194029e-05, "epoch": 0.3947858472998138, "percentage": 7.91, "elapsed_time": "0:12:04", "remaining_time": "2:20:32"} {"current_steps": 54, "total_steps": 670, "loss": 0.0318, "lr": 8.059701492537314e-05, "epoch": 0.4022346368715084, "percentage": 8.06, "elapsed_time": "0:12:17", "remaining_time": "2:20:13"} {"current_steps": 55, "total_steps": 670, "loss": 0.034, "lr": 8.208955223880597e-05, "epoch": 0.409683426443203, "percentage": 8.21, "elapsed_time": "0:12:31", "remaining_time": "2:20:00"} {"current_steps": 55, "total_steps": 670, "eval_loss": 0.03625323995947838, "epoch": 0.409683426443203, "percentage": 8.21, "elapsed_time": "0:12:32", "remaining_time": "2:20:16"} {"current_steps": 56, "total_steps": 670, "loss": 0.0349, "lr": 8.358208955223881e-05, "epoch": 0.4171322160148976, "percentage": 8.36, "elapsed_time": "0:12:45", "remaining_time": "2:19:54"} {"current_steps": 57, "total_steps": 670, "loss": 0.032, "lr": 8.507462686567164e-05, "epoch": 0.4245810055865922, "percentage": 8.51, "elapsed_time": "0:12:58", "remaining_time": "2:19:37"} {"current_steps": 58, "total_steps": 670, "loss": 0.0329, "lr": 8.656716417910447e-05, "epoch": 0.43202979515828677, "percentage": 8.66, "elapsed_time": "0:13:13", "remaining_time": "2:19:29"} {"current_steps": 59, "total_steps": 670, "loss": 0.0303, "lr": 8.805970149253732e-05, "epoch": 0.43947858472998136, "percentage": 8.81, "elapsed_time": "0:13:25", "remaining_time": "2:19:03"} {"current_steps": 60, "total_steps": 670, "loss": 0.0325, "lr": 8.955223880597016e-05, "epoch": 0.44692737430167595, "percentage": 8.96, "elapsed_time": "0:13:38", "remaining_time": "2:18:44"} {"current_steps": 60, "total_steps": 670, "eval_loss": 0.034458719193935394, "epoch": 0.44692737430167595, "percentage": 8.96, "elapsed_time": "0:13:40", "remaining_time": "2:18:59"} {"current_steps": 61, "total_steps": 670, "loss": 0.0306, "lr": 9.104477611940299e-05, "epoch": 0.4543761638733706, "percentage": 9.1, "elapsed_time": "0:13:52", "remaining_time": "2:18:32"} {"current_steps": 62, "total_steps": 670, "loss": 0.0307, "lr": 9.253731343283582e-05, "epoch": 0.4618249534450652, "percentage": 9.25, "elapsed_time": "0:14:05", "remaining_time": "2:18:12"} {"current_steps": 63, "total_steps": 670, "loss": 0.0294, "lr": 9.402985074626867e-05, "epoch": 0.4692737430167598, "percentage": 9.4, "elapsed_time": "0:14:18", "remaining_time": "2:17:53"} {"current_steps": 64, "total_steps": 670, "loss": 0.0298, "lr": 9.552238805970149e-05, "epoch": 0.4767225325884544, "percentage": 9.55, "elapsed_time": "0:14:31", "remaining_time": "2:17:29"} {"current_steps": 65, "total_steps": 670, "loss": 0.0299, "lr": 9.701492537313434e-05, "epoch": 0.48417132216014896, "percentage": 9.7, "elapsed_time": "0:14:44", "remaining_time": "2:17:08"} {"current_steps": 65, "total_steps": 670, "eval_loss": 0.03305283561348915, "epoch": 0.48417132216014896, "percentage": 9.7, "elapsed_time": "0:14:45", "remaining_time": "2:17:21"} {"current_steps": 66, "total_steps": 670, "loss": 0.0284, "lr": 9.850746268656717e-05, "epoch": 0.49162011173184356, "percentage": 9.85, "elapsed_time": "0:14:59", "remaining_time": "2:17:11"} {"current_steps": 67, "total_steps": 670, "loss": 0.0324, "lr": 0.0001, "epoch": 0.49906890130353815, "percentage": 10.0, "elapsed_time": "0:15:11", "remaining_time": "2:16:47"} {"current_steps": 68, "total_steps": 670, "loss": 0.0364, "lr": 9.999932141516873e-05, "epoch": 0.5065176908752328, "percentage": 10.15, "elapsed_time": "0:15:25", "remaining_time": "2:16:36"} {"current_steps": 69, "total_steps": 670, "loss": 0.031, "lr": 9.999728567909403e-05, "epoch": 0.5139664804469274, "percentage": 10.3, "elapsed_time": "0:15:39", "remaining_time": "2:16:20"} {"current_steps": 70, "total_steps": 670, "loss": 0.0286, "lr": 9.999389284703265e-05, "epoch": 0.521415270018622, "percentage": 10.45, "elapsed_time": "0:15:53", "remaining_time": "2:16:10"} {"current_steps": 70, "total_steps": 670, "eval_loss": 0.03126455098390579, "epoch": 0.521415270018622, "percentage": 10.45, "elapsed_time": "0:15:54", "remaining_time": "2:16:22"} {"current_steps": 71, "total_steps": 670, "loss": 0.0313, "lr": 9.99891430110776e-05, "epoch": 0.5288640595903166, "percentage": 10.6, "elapsed_time": "0:16:08", "remaining_time": "2:16:14"} {"current_steps": 72, "total_steps": 670, "loss": 0.0269, "lr": 9.998303630015553e-05, "epoch": 0.5363128491620112, "percentage": 10.75, "elapsed_time": "0:16:22", "remaining_time": "2:16:01"} {"current_steps": 73, "total_steps": 670, "loss": 0.0277, "lr": 9.99755728800233e-05, "epoch": 0.5437616387337058, "percentage": 10.9, "elapsed_time": "0:16:35", "remaining_time": "2:15:42"} {"current_steps": 74, "total_steps": 670, "loss": 0.0269, "lr": 9.996675295326346e-05, "epoch": 0.5512104283054003, "percentage": 11.04, "elapsed_time": "0:16:49", "remaining_time": "2:15:30"} {"current_steps": 75, "total_steps": 670, "loss": 0.0299, "lr": 9.995657675927874e-05, "epoch": 0.5586592178770949, "percentage": 11.19, "elapsed_time": "0:17:03", "remaining_time": "2:15:16"} {"current_steps": 75, "total_steps": 670, "eval_loss": 0.029203444719314575, "epoch": 0.5586592178770949, "percentage": 11.19, "elapsed_time": "0:17:04", "remaining_time": "2:15:27"} {"current_steps": 76, "total_steps": 670, "loss": 0.0251, "lr": 9.994504457428558e-05, "epoch": 0.5661080074487895, "percentage": 11.34, "elapsed_time": "0:17:18", "remaining_time": "2:15:12"} {"current_steps": 77, "total_steps": 670, "loss": 0.0282, "lr": 9.993215671130662e-05, "epoch": 0.5735567970204841, "percentage": 11.49, "elapsed_time": "0:17:31", "remaining_time": "2:14:59"} {"current_steps": 78, "total_steps": 670, "loss": 0.0235, "lr": 9.991791352016217e-05, "epoch": 0.5810055865921788, "percentage": 11.64, "elapsed_time": "0:17:44", "remaining_time": "2:14:36"} {"current_steps": 79, "total_steps": 670, "loss": 0.0265, "lr": 9.99023153874608e-05, "epoch": 0.5884543761638734, "percentage": 11.79, "elapsed_time": "0:17:58", "remaining_time": "2:14:26"} {"current_steps": 80, "total_steps": 670, "loss": 0.028, "lr": 9.988536273658876e-05, "epoch": 0.595903165735568, "percentage": 11.94, "elapsed_time": "0:18:11", "remaining_time": "2:14:11"} {"current_steps": 80, "total_steps": 670, "eval_loss": 0.027607519179582596, "epoch": 0.595903165735568, "percentage": 11.94, "elapsed_time": "0:18:13", "remaining_time": "2:14:23"} {"current_steps": 81, "total_steps": 670, "loss": 0.0268, "lr": 9.986705602769847e-05, "epoch": 0.6033519553072626, "percentage": 12.09, "elapsed_time": "0:18:27", "remaining_time": "2:14:11"} {"current_steps": 82, "total_steps": 670, "loss": 0.0247, "lr": 9.984739575769618e-05, "epoch": 0.6108007448789572, "percentage": 12.24, "elapsed_time": "0:18:40", "remaining_time": "2:13:55"} {"current_steps": 83, "total_steps": 670, "loss": 0.025, "lr": 9.982638246022831e-05, "epoch": 0.6182495344506518, "percentage": 12.39, "elapsed_time": "0:18:54", "remaining_time": "2:13:43"} {"current_steps": 84, "total_steps": 670, "loss": 0.0228, "lr": 9.980401670566706e-05, "epoch": 0.6256983240223464, "percentage": 12.54, "elapsed_time": "0:19:08", "remaining_time": "2:13:29"} {"current_steps": 85, "total_steps": 670, "loss": 0.025, "lr": 9.978029910109491e-05, "epoch": 0.633147113594041, "percentage": 12.69, "elapsed_time": "0:19:22", "remaining_time": "2:13:17"} {"current_steps": 85, "total_steps": 670, "eval_loss": 0.026060376316308975, "epoch": 0.633147113594041, "percentage": 12.69, "elapsed_time": "0:19:23", "remaining_time": "2:13:27"} {"current_steps": 86, "total_steps": 670, "loss": 0.0265, "lr": 9.975523029028811e-05, "epoch": 0.6405959031657356, "percentage": 12.84, "elapsed_time": "0:19:36", "remaining_time": "2:13:07"} {"current_steps": 87, "total_steps": 670, "loss": 0.0267, "lr": 9.972881095369926e-05, "epoch": 0.6480446927374302, "percentage": 12.99, "elapsed_time": "0:19:49", "remaining_time": "2:12:49"} {"current_steps": 88, "total_steps": 670, "loss": 0.0262, "lr": 9.97010418084388e-05, "epoch": 0.6554934823091247, "percentage": 13.13, "elapsed_time": "0:20:01", "remaining_time": "2:12:29"} {"current_steps": 89, "total_steps": 670, "loss": 0.0213, "lr": 9.967192360825557e-05, "epoch": 0.6629422718808193, "percentage": 13.28, "elapsed_time": "0:20:14", "remaining_time": "2:12:10"} {"current_steps": 90, "total_steps": 670, "loss": 0.024, "lr": 9.964145714351631e-05, "epoch": 0.6703910614525139, "percentage": 13.43, "elapsed_time": "0:20:27", "remaining_time": "2:11:52"} {"current_steps": 90, "total_steps": 670, "eval_loss": 0.02484722062945366, "epoch": 0.6703910614525139, "percentage": 13.43, "elapsed_time": "0:20:29", "remaining_time": "2:12:01"} {"current_steps": 91, "total_steps": 670, "loss": 0.0254, "lr": 9.960964324118426e-05, "epoch": 0.6778398510242085, "percentage": 13.58, "elapsed_time": "0:20:43", "remaining_time": "2:11:49"} {"current_steps": 92, "total_steps": 670, "loss": 0.0242, "lr": 9.95764827647967e-05, "epoch": 0.6852886405959032, "percentage": 13.73, "elapsed_time": "0:20:56", "remaining_time": "2:11:33"} {"current_steps": 93, "total_steps": 670, "loss": 0.0226, "lr": 9.954197661444147e-05, "epoch": 0.6927374301675978, "percentage": 13.88, "elapsed_time": "0:21:10", "remaining_time": "2:11:23"} {"current_steps": 94, "total_steps": 670, "loss": 0.0263, "lr": 9.950612572673255e-05, "epoch": 0.7001862197392924, "percentage": 14.03, "elapsed_time": "0:21:24", "remaining_time": "2:11:08"} {"current_steps": 95, "total_steps": 670, "loss": 0.0231, "lr": 9.946893107478473e-05, "epoch": 0.707635009310987, "percentage": 14.18, "elapsed_time": "0:21:39", "remaining_time": "2:11:03"} {"current_steps": 95, "total_steps": 670, "eval_loss": 0.024149179458618164, "epoch": 0.707635009310987, "percentage": 14.18, "elapsed_time": "0:21:40", "remaining_time": "2:11:11"} {"current_steps": 96, "total_steps": 670, "loss": 0.0239, "lr": 9.943039366818704e-05, "epoch": 0.7150837988826816, "percentage": 14.33, "elapsed_time": "0:21:53", "remaining_time": "2:10:53"} {"current_steps": 97, "total_steps": 670, "loss": 0.024, "lr": 9.939051455297547e-05, "epoch": 0.7225325884543762, "percentage": 14.48, "elapsed_time": "0:22:06", "remaining_time": "2:10:37"} {"current_steps": 98, "total_steps": 670, "loss": 0.0219, "lr": 9.934929481160455e-05, "epoch": 0.7299813780260708, "percentage": 14.63, "elapsed_time": "0:22:19", "remaining_time": "2:10:15"} {"current_steps": 99, "total_steps": 670, "loss": 0.0211, "lr": 9.93067355629179e-05, "epoch": 0.7374301675977654, "percentage": 14.78, "elapsed_time": "0:22:32", "remaining_time": "2:09:59"} {"current_steps": 100, "total_steps": 670, "loss": 0.0222, "lr": 9.926283796211795e-05, "epoch": 0.74487895716946, "percentage": 14.93, "elapsed_time": "0:22:45", "remaining_time": "2:09:43"} {"current_steps": 100, "total_steps": 670, "eval_loss": 0.02335224486887455, "epoch": 0.74487895716946, "percentage": 14.93, "elapsed_time": "0:22:46", "remaining_time": "2:09:51"} {"current_steps": 101, "total_steps": 670, "loss": 0.023, "lr": 9.921760320073456e-05, "epoch": 0.7523277467411545, "percentage": 15.07, "elapsed_time": "0:23:01", "remaining_time": "2:09:43"} {"current_steps": 102, "total_steps": 670, "loss": 0.0237, "lr": 9.917103250659262e-05, "epoch": 0.7597765363128491, "percentage": 15.22, "elapsed_time": "0:23:13", "remaining_time": "2:09:20"} {"current_steps": 103, "total_steps": 670, "loss": 0.0218, "lr": 9.91231271437788e-05, "epoch": 0.7672253258845437, "percentage": 15.37, "elapsed_time": "0:23:26", "remaining_time": "2:09:00"} {"current_steps": 104, "total_steps": 670, "loss": 0.0183, "lr": 9.907388841260723e-05, "epoch": 0.7746741154562383, "percentage": 15.52, "elapsed_time": "0:23:38", "remaining_time": "2:08:41"} {"current_steps": 105, "total_steps": 670, "loss": 0.021, "lr": 9.902331764958413e-05, "epoch": 0.7821229050279329, "percentage": 15.67, "elapsed_time": "0:23:51", "remaining_time": "2:08:24"} {"current_steps": 105, "total_steps": 670, "eval_loss": 0.022850122302770615, "epoch": 0.7821229050279329, "percentage": 15.67, "elapsed_time": "0:23:53", "remaining_time": "2:08:32"} {"current_steps": 106, "total_steps": 670, "loss": 0.022, "lr": 9.89714162273716e-05, "epoch": 0.7895716945996276, "percentage": 15.82, "elapsed_time": "0:24:06", "remaining_time": "2:08:17"} {"current_steps": 107, "total_steps": 670, "loss": 0.0201, "lr": 9.891818555475037e-05, "epoch": 0.7970204841713222, "percentage": 15.97, "elapsed_time": "0:24:20", "remaining_time": "2:08:03"} {"current_steps": 108, "total_steps": 670, "loss": 0.0227, "lr": 9.886362707658152e-05, "epoch": 0.8044692737430168, "percentage": 16.12, "elapsed_time": "0:24:33", "remaining_time": "2:07:47"} {"current_steps": 109, "total_steps": 670, "loss": 0.0207, "lr": 9.880774227376726e-05, "epoch": 0.8119180633147114, "percentage": 16.27, "elapsed_time": "0:24:47", "remaining_time": "2:07:38"} {"current_steps": 110, "total_steps": 670, "loss": 0.0228, "lr": 9.87505326632108e-05, "epoch": 0.819366852886406, "percentage": 16.42, "elapsed_time": "0:25:00", "remaining_time": "2:07:20"} {"current_steps": 110, "total_steps": 670, "eval_loss": 0.022170543670654297, "epoch": 0.819366852886406, "percentage": 16.42, "elapsed_time": "0:25:02", "remaining_time": "2:07:27"} {"current_steps": 111, "total_steps": 670, "loss": 0.0207, "lr": 9.869199979777505e-05, "epoch": 0.8268156424581006, "percentage": 16.57, "elapsed_time": "0:25:15", "remaining_time": "2:07:13"} {"current_steps": 112, "total_steps": 670, "loss": 0.0199, "lr": 9.863214526624065e-05, "epoch": 0.8342644320297952, "percentage": 16.72, "elapsed_time": "0:25:29", "remaining_time": "2:07:00"} {"current_steps": 113, "total_steps": 670, "loss": 0.0212, "lr": 9.857097069326267e-05, "epoch": 0.8417132216014898, "percentage": 16.87, "elapsed_time": "0:25:42", "remaining_time": "2:06:43"} {"current_steps": 114, "total_steps": 670, "loss": 0.0231, "lr": 9.850847773932656e-05, "epoch": 0.8491620111731844, "percentage": 17.01, "elapsed_time": "0:25:55", "remaining_time": "2:06:26"} {"current_steps": 115, "total_steps": 670, "loss": 0.0184, "lr": 9.844466810070319e-05, "epoch": 0.8566108007448789, "percentage": 17.16, "elapsed_time": "0:26:09", "remaining_time": "2:06:13"} {"current_steps": 115, "total_steps": 670, "eval_loss": 0.02158324047923088, "epoch": 0.8566108007448789, "percentage": 17.16, "elapsed_time": "0:26:10", "remaining_time": "2:06:20"} {"current_steps": 116, "total_steps": 670, "loss": 0.0214, "lr": 9.837954350940266e-05, "epoch": 0.8640595903165735, "percentage": 17.31, "elapsed_time": "0:26:24", "remaining_time": "2:06:07"} {"current_steps": 117, "total_steps": 670, "loss": 0.0214, "lr": 9.831310573312736e-05, "epoch": 0.8715083798882681, "percentage": 17.46, "elapsed_time": "0:26:38", "remaining_time": "2:05:54"} {"current_steps": 118, "total_steps": 670, "loss": 0.021, "lr": 9.824535657522398e-05, "epoch": 0.8789571694599627, "percentage": 17.61, "elapsed_time": "0:26:51", "remaining_time": "2:05:36"} {"current_steps": 119, "total_steps": 670, "loss": 0.0206, "lr": 9.817629787463456e-05, "epoch": 0.8864059590316573, "percentage": 17.76, "elapsed_time": "0:27:05", "remaining_time": "2:05:24"} {"current_steps": 120, "total_steps": 670, "loss": 0.0227, "lr": 9.810593150584658e-05, "epoch": 0.8938547486033519, "percentage": 17.91, "elapsed_time": "0:27:19", "remaining_time": "2:05:12"} {"current_steps": 120, "total_steps": 670, "eval_loss": 0.021058350801467896, "epoch": 0.8938547486033519, "percentage": 17.91, "elapsed_time": "0:27:20", "remaining_time": "2:05:19"} {"current_steps": 121, "total_steps": 670, "loss": 0.0223, "lr": 9.8034259378842e-05, "epoch": 0.9013035381750466, "percentage": 18.06, "elapsed_time": "0:27:34", "remaining_time": "2:05:05"} {"current_steps": 122, "total_steps": 670, "loss": 0.0231, "lr": 9.796128343904562e-05, "epoch": 0.9087523277467412, "percentage": 18.21, "elapsed_time": "0:27:47", "remaining_time": "2:04:49"} {"current_steps": 123, "total_steps": 670, "loss": 0.0239, "lr": 9.788700566727205e-05, "epoch": 0.9162011173184358, "percentage": 18.36, "elapsed_time": "0:28:01", "remaining_time": "2:04:37"} {"current_steps": 124, "total_steps": 670, "loss": 0.0207, "lr": 9.781142807967205e-05, "epoch": 0.9236499068901304, "percentage": 18.51, "elapsed_time": "0:28:14", "remaining_time": "2:04:23"} {"current_steps": 125, "total_steps": 670, "loss": 0.0188, "lr": 9.773455272767779e-05, "epoch": 0.931098696461825, "percentage": 18.66, "elapsed_time": "0:28:28", "remaining_time": "2:04:07"} {"current_steps": 125, "total_steps": 670, "eval_loss": 0.020916979759931564, "epoch": 0.931098696461825, "percentage": 18.66, "elapsed_time": "0:28:29", "remaining_time": "2:04:13"} {"current_steps": 126, "total_steps": 670, "loss": 0.02, "lr": 9.765638169794719e-05, "epoch": 0.9385474860335196, "percentage": 18.81, "elapsed_time": "0:28:43", "remaining_time": "2:04:01"} {"current_steps": 127, "total_steps": 670, "loss": 0.0237, "lr": 9.757691711230727e-05, "epoch": 0.9459962756052142, "percentage": 18.96, "elapsed_time": "0:28:56", "remaining_time": "2:03:45"} {"current_steps": 128, "total_steps": 670, "loss": 0.0205, "lr": 9.74961611276965e-05, "epoch": 0.9534450651769087, "percentage": 19.1, "elapsed_time": "0:29:10", "remaining_time": "2:03:31"} {"current_steps": 129, "total_steps": 670, "loss": 0.0245, "lr": 9.741411593610635e-05, "epoch": 0.9608938547486033, "percentage": 19.25, "elapsed_time": "0:29:24", "remaining_time": "2:03:19"} {"current_steps": 130, "total_steps": 670, "loss": 0.0238, "lr": 9.733078376452171e-05, "epoch": 0.9683426443202979, "percentage": 19.4, "elapsed_time": "0:29:37", "remaining_time": "2:03:03"} {"current_steps": 130, "total_steps": 670, "eval_loss": 0.02051009237766266, "epoch": 0.9683426443202979, "percentage": 19.4, "elapsed_time": "0:29:38", "remaining_time": "2:03:09"} {"current_steps": 131, "total_steps": 670, "loss": 0.0213, "lr": 9.724616687486048e-05, "epoch": 0.9757914338919925, "percentage": 19.55, "elapsed_time": "0:29:51", "remaining_time": "2:02:51"} {"current_steps": 132, "total_steps": 670, "loss": 0.018, "lr": 9.716026756391217e-05, "epoch": 0.9832402234636871, "percentage": 19.7, "elapsed_time": "0:30:04", "remaining_time": "2:02:36"} {"current_steps": 133, "total_steps": 670, "loss": 0.0175, "lr": 9.707308816327557e-05, "epoch": 0.9906890130353817, "percentage": 19.85, "elapsed_time": "0:30:18", "remaining_time": "2:02:22"} {"current_steps": 134, "total_steps": 670, "loss": 0.021, "lr": 9.698463103929542e-05, "epoch": 0.9981378026070763, "percentage": 20.0, "elapsed_time": "0:30:31", "remaining_time": "2:02:04"} {"current_steps": 135, "total_steps": 670, "loss": 0.0328, "lr": 9.689489859299823e-05, "epoch": 1.005586592178771, "percentage": 20.15, "elapsed_time": "0:30:44", "remaining_time": "2:01:49"} {"current_steps": 135, "total_steps": 670, "eval_loss": 0.02007954940199852, "epoch": 1.005586592178771, "percentage": 20.15, "elapsed_time": "0:30:45", "remaining_time": "2:01:55"} {"current_steps": 136, "total_steps": 670, "loss": 0.0196, "lr": 9.680389326002708e-05, "epoch": 1.0130353817504656, "percentage": 20.3, "elapsed_time": "0:30:59", "remaining_time": "2:01:42"} {"current_steps": 137, "total_steps": 670, "loss": 0.0217, "lr": 9.671161751057551e-05, "epoch": 1.0204841713221602, "percentage": 20.45, "elapsed_time": "0:31:12", "remaining_time": "2:01:25"} {"current_steps": 138, "total_steps": 670, "loss": 0.0204, "lr": 9.661807384932047e-05, "epoch": 1.0279329608938548, "percentage": 20.6, "elapsed_time": "0:31:26", "remaining_time": "2:01:12"} {"current_steps": 139, "total_steps": 670, "loss": 0.0206, "lr": 9.652326481535435e-05, "epoch": 1.0353817504655494, "percentage": 20.75, "elapsed_time": "0:31:40", "remaining_time": "2:00:59"} {"current_steps": 140, "total_steps": 670, "loss": 0.0208, "lr": 9.642719298211602e-05, "epoch": 1.042830540037244, "percentage": 20.9, "elapsed_time": "0:31:53", "remaining_time": "2:00:42"} {"current_steps": 140, "total_steps": 670, "eval_loss": 0.019787099212408066, "epoch": 1.042830540037244, "percentage": 20.9, "elapsed_time": "0:31:54", "remaining_time": "2:00:48"} {"current_steps": 141, "total_steps": 670, "loss": 0.0184, "lr": 9.632986095732107e-05, "epoch": 1.0502793296089385, "percentage": 21.04, "elapsed_time": "0:32:08", "remaining_time": "2:00:35"} {"current_steps": 142, "total_steps": 670, "loss": 0.02, "lr": 9.623127138289087e-05, "epoch": 1.0577281191806331, "percentage": 21.19, "elapsed_time": "0:32:21", "remaining_time": "2:00:19"} {"current_steps": 143, "total_steps": 670, "loss": 0.0183, "lr": 9.613142693488106e-05, "epoch": 1.0651769087523277, "percentage": 21.34, "elapsed_time": "0:32:34", "remaining_time": "2:00:02"} {"current_steps": 144, "total_steps": 670, "loss": 0.0171, "lr": 9.603033032340875e-05, "epoch": 1.0726256983240223, "percentage": 21.49, "elapsed_time": "0:32:48", "remaining_time": "1:59:51"} {"current_steps": 145, "total_steps": 670, "loss": 0.0199, "lr": 9.5927984292579e-05, "epoch": 1.080074487895717, "percentage": 21.64, "elapsed_time": "0:33:02", "remaining_time": "1:59:37"} {"current_steps": 145, "total_steps": 670, "eval_loss": 0.019386105239391327, "epoch": 1.080074487895717, "percentage": 21.64, "elapsed_time": "0:33:03", "remaining_time": "1:59:42"} {"current_steps": 146, "total_steps": 670, "loss": 0.0177, "lr": 9.582439162041037e-05, "epoch": 1.0875232774674115, "percentage": 21.79, "elapsed_time": "0:33:16", "remaining_time": "1:59:26"} {"current_steps": 147, "total_steps": 670, "loss": 0.0163, "lr": 9.571955511875954e-05, "epoch": 1.094972067039106, "percentage": 21.94, "elapsed_time": "0:33:29", "remaining_time": "1:59:09"} {"current_steps": 148, "total_steps": 670, "loss": 0.0205, "lr": 9.561347763324484e-05, "epoch": 1.1024208566108007, "percentage": 22.09, "elapsed_time": "0:33:42", "remaining_time": "1:58:55"} {"current_steps": 149, "total_steps": 670, "loss": 0.0211, "lr": 9.550616204316922e-05, "epoch": 1.1098696461824953, "percentage": 22.24, "elapsed_time": "0:33:56", "remaining_time": "1:58:40"} {"current_steps": 150, "total_steps": 670, "loss": 0.0201, "lr": 9.539761126144193e-05, "epoch": 1.1173184357541899, "percentage": 22.39, "elapsed_time": "0:34:09", "remaining_time": "1:58:23"} {"current_steps": 150, "total_steps": 670, "eval_loss": 0.01909106783568859, "epoch": 1.1173184357541899, "percentage": 22.39, "elapsed_time": "0:34:10", "remaining_time": "1:58:28"} {"current_steps": 151, "total_steps": 670, "loss": 0.0184, "lr": 9.528782823449954e-05, "epoch": 1.1247672253258845, "percentage": 22.54, "elapsed_time": "0:34:24", "remaining_time": "1:58:16"} {"current_steps": 152, "total_steps": 670, "loss": 0.0181, "lr": 9.517681594222589e-05, "epoch": 1.132216014897579, "percentage": 22.69, "elapsed_time": "0:34:37", "remaining_time": "1:58:01"} {"current_steps": 153, "total_steps": 670, "loss": 0.0222, "lr": 9.506457739787132e-05, "epoch": 1.1396648044692737, "percentage": 22.84, "elapsed_time": "0:34:50", "remaining_time": "1:57:44"} {"current_steps": 154, "total_steps": 670, "loss": 0.0206, "lr": 9.495111564797074e-05, "epoch": 1.1471135940409685, "percentage": 22.99, "elapsed_time": "0:35:04", "remaining_time": "1:57:33"} {"current_steps": 155, "total_steps": 670, "loss": 0.0163, "lr": 9.483643377226107e-05, "epoch": 1.1545623836126628, "percentage": 23.13, "elapsed_time": "0:35:19", "remaining_time": "1:57:21"} {"current_steps": 155, "total_steps": 670, "eval_loss": 0.018878690898418427, "epoch": 1.1545623836126628, "percentage": 23.13, "elapsed_time": "0:35:20", "remaining_time": "1:57:26"} {"current_steps": 156, "total_steps": 670, "loss": 0.0176, "lr": 9.472053488359757e-05, "epoch": 1.1620111731843576, "percentage": 23.28, "elapsed_time": "0:35:35", "remaining_time": "1:57:15"} {"current_steps": 157, "total_steps": 670, "loss": 0.0181, "lr": 9.460342212786932e-05, "epoch": 1.169459962756052, "percentage": 23.43, "elapsed_time": "0:35:49", "remaining_time": "1:57:02"} {"current_steps": 158, "total_steps": 670, "loss": 0.0186, "lr": 9.448509868391395e-05, "epoch": 1.1769087523277468, "percentage": 23.58, "elapsed_time": "0:36:03", "remaining_time": "1:56:49"} {"current_steps": 159, "total_steps": 670, "loss": 0.0193, "lr": 9.43655677634312e-05, "epoch": 1.1843575418994414, "percentage": 23.73, "elapsed_time": "0:36:16", "remaining_time": "1:56:34"} {"current_steps": 160, "total_steps": 670, "loss": 0.0164, "lr": 9.424483261089584e-05, "epoch": 1.191806331471136, "percentage": 23.88, "elapsed_time": "0:36:29", "remaining_time": "1:56:19"} {"current_steps": 160, "total_steps": 670, "eval_loss": 0.018638966605067253, "epoch": 1.191806331471136, "percentage": 23.88, "elapsed_time": "0:36:31", "remaining_time": "1:56:24"} {"current_steps": 161, "total_steps": 670, "loss": 0.0187, "lr": 9.412289650346961e-05, "epoch": 1.1992551210428306, "percentage": 24.03, "elapsed_time": "0:36:44", "remaining_time": "1:56:09"} {"current_steps": 162, "total_steps": 670, "loss": 0.0171, "lr": 9.399976275091223e-05, "epoch": 1.2067039106145252, "percentage": 24.18, "elapsed_time": "0:36:58", "remaining_time": "1:55:56"} {"current_steps": 163, "total_steps": 670, "loss": 0.0195, "lr": 9.387543469549156e-05, "epoch": 1.2141527001862198, "percentage": 24.33, "elapsed_time": "0:37:11", "remaining_time": "1:55:40"} {"current_steps": 164, "total_steps": 670, "loss": 0.0212, "lr": 9.374991571189291e-05, "epoch": 1.2216014897579144, "percentage": 24.48, "elapsed_time": "0:37:25", "remaining_time": "1:55:27"} {"current_steps": 165, "total_steps": 670, "loss": 0.0174, "lr": 9.362320920712739e-05, "epoch": 1.229050279329609, "percentage": 24.63, "elapsed_time": "0:37:38", "remaining_time": "1:55:13"} {"current_steps": 165, "total_steps": 670, "eval_loss": 0.018519219011068344, "epoch": 1.229050279329609, "percentage": 24.63, "elapsed_time": "0:37:40", "remaining_time": "1:55:17"} {"current_steps": 166, "total_steps": 670, "loss": 0.0178, "lr": 9.349531862043952e-05, "epoch": 1.2364990689013036, "percentage": 24.78, "elapsed_time": "0:37:53", "remaining_time": "1:55:03"} {"current_steps": 167, "total_steps": 670, "loss": 0.0179, "lr": 9.336624742321375e-05, "epoch": 1.2439478584729982, "percentage": 24.93, "elapsed_time": "0:38:07", "remaining_time": "1:54:49"} {"current_steps": 168, "total_steps": 670, "loss": 0.0179, "lr": 9.323599911888037e-05, "epoch": 1.2513966480446927, "percentage": 25.07, "elapsed_time": "0:38:20", "remaining_time": "1:54:33"} {"current_steps": 169, "total_steps": 670, "loss": 0.0183, "lr": 9.310457724282034e-05, "epoch": 1.2588454376163873, "percentage": 25.22, "elapsed_time": "0:38:34", "remaining_time": "1:54:20"} {"current_steps": 170, "total_steps": 670, "loss": 0.0175, "lr": 9.297198536226928e-05, "epoch": 1.266294227188082, "percentage": 25.37, "elapsed_time": "0:38:47", "remaining_time": "1:54:06"} {"current_steps": 170, "total_steps": 670, "eval_loss": 0.018166562542319298, "epoch": 1.266294227188082, "percentage": 25.37, "elapsed_time": "0:38:49", "remaining_time": "1:54:10"} {"current_steps": 171, "total_steps": 670, "loss": 0.0174, "lr": 9.283822707622075e-05, "epoch": 1.2737430167597765, "percentage": 25.52, "elapsed_time": "0:39:03", "remaining_time": "1:53:58"} {"current_steps": 172, "total_steps": 670, "loss": 0.017, "lr": 9.270330601532855e-05, "epoch": 1.2811918063314711, "percentage": 25.67, "elapsed_time": "0:39:17", "remaining_time": "1:53:44"} {"current_steps": 173, "total_steps": 670, "loss": 0.0198, "lr": 9.256722584180806e-05, "epoch": 1.2886405959031657, "percentage": 25.82, "elapsed_time": "0:39:29", "remaining_time": "1:53:28"} {"current_steps": 174, "total_steps": 670, "loss": 0.0196, "lr": 9.242999024933694e-05, "epoch": 1.2960893854748603, "percentage": 25.97, "elapsed_time": "0:39:42", "remaining_time": "1:53:10"} {"current_steps": 175, "total_steps": 670, "loss": 0.0175, "lr": 9.229160296295488e-05, "epoch": 1.303538175046555, "percentage": 26.12, "elapsed_time": "0:39:55", "remaining_time": "1:52:56"} {"current_steps": 175, "total_steps": 670, "eval_loss": 0.01796720176935196, "epoch": 1.303538175046555, "percentage": 26.12, "elapsed_time": "0:39:56", "remaining_time": "1:52:59"} {"current_steps": 176, "total_steps": 670, "loss": 0.0171, "lr": 9.215206773896237e-05, "epoch": 1.3109869646182495, "percentage": 26.27, "elapsed_time": "0:40:08", "remaining_time": "1:52:41"} {"current_steps": 177, "total_steps": 670, "loss": 0.0197, "lr": 9.201138836481891e-05, "epoch": 1.318435754189944, "percentage": 26.42, "elapsed_time": "0:40:22", "remaining_time": "1:52:27"} {"current_steps": 178, "total_steps": 670, "loss": 0.015, "lr": 9.186956865904003e-05, "epoch": 1.3258845437616387, "percentage": 26.57, "elapsed_time": "0:40:36", "remaining_time": "1:52:14"} {"current_steps": 179, "total_steps": 670, "loss": 0.0219, "lr": 9.172661247109382e-05, "epoch": 1.3333333333333333, "percentage": 26.72, "elapsed_time": "0:40:49", "remaining_time": "1:51:59"} {"current_steps": 180, "total_steps": 670, "loss": 0.0184, "lr": 9.158252368129628e-05, "epoch": 1.3407821229050279, "percentage": 26.87, "elapsed_time": "0:41:03", "remaining_time": "1:51:45"} {"current_steps": 180, "total_steps": 670, "eval_loss": 0.017505526542663574, "epoch": 1.3407821229050279, "percentage": 26.87, "elapsed_time": "0:41:04", "remaining_time": "1:51:49"} {"current_steps": 181, "total_steps": 670, "loss": 0.0229, "lr": 9.143730620070608e-05, "epoch": 1.3482309124767227, "percentage": 27.01, "elapsed_time": "0:41:17", "remaining_time": "1:51:33"} {"current_steps": 182, "total_steps": 670, "loss": 0.0153, "lr": 9.129096397101843e-05, "epoch": 1.355679702048417, "percentage": 27.16, "elapsed_time": "0:41:31", "remaining_time": "1:51:19"} {"current_steps": 183, "total_steps": 670, "loss": 0.0179, "lr": 9.114350096445803e-05, "epoch": 1.3631284916201118, "percentage": 27.31, "elapsed_time": "0:41:44", "remaining_time": "1:51:06"} {"current_steps": 184, "total_steps": 670, "loss": 0.016, "lr": 9.099492118367123e-05, "epoch": 1.3705772811918062, "percentage": 27.46, "elapsed_time": "0:41:57", "remaining_time": "1:50:49"} {"current_steps": 185, "total_steps": 670, "loss": 0.0185, "lr": 9.084522866161746e-05, "epoch": 1.378026070763501, "percentage": 27.61, "elapsed_time": "0:42:11", "remaining_time": "1:50:35"} {"current_steps": 185, "total_steps": 670, "eval_loss": 0.017372244969010353, "epoch": 1.378026070763501, "percentage": 27.61, "elapsed_time": "0:42:12", "remaining_time": "1:50:39"} {"current_steps": 186, "total_steps": 670, "loss": 0.0178, "lr": 9.069442746145971e-05, "epoch": 1.3854748603351954, "percentage": 27.76, "elapsed_time": "0:42:25", "remaining_time": "1:50:23"} {"current_steps": 187, "total_steps": 670, "loss": 0.0161, "lr": 9.054252167645425e-05, "epoch": 1.3929236499068902, "percentage": 27.91, "elapsed_time": "0:42:38", "remaining_time": "1:50:08"} {"current_steps": 188, "total_steps": 670, "loss": 0.0183, "lr": 9.038951542983956e-05, "epoch": 1.4003724394785848, "percentage": 28.06, "elapsed_time": "0:42:51", "remaining_time": "1:49:52"} {"current_steps": 189, "total_steps": 670, "loss": 0.0191, "lr": 9.023541287472435e-05, "epoch": 1.4078212290502794, "percentage": 28.21, "elapsed_time": "0:43:04", "remaining_time": "1:49:37"} {"current_steps": 190, "total_steps": 670, "loss": 0.0155, "lr": 9.008021819397487e-05, "epoch": 1.415270018621974, "percentage": 28.36, "elapsed_time": "0:43:18", "remaining_time": "1:49:24"} {"current_steps": 190, "total_steps": 670, "eval_loss": 0.017318665981292725, "epoch": 1.415270018621974, "percentage": 28.36, "elapsed_time": "0:43:19", "remaining_time": "1:49:27"} {"current_steps": 191, "total_steps": 670, "loss": 0.0157, "lr": 8.992393560010137e-05, "epoch": 1.4227188081936686, "percentage": 28.51, "elapsed_time": "0:43:33", "remaining_time": "1:49:13"} {"current_steps": 192, "total_steps": 670, "loss": 0.0192, "lr": 8.976656933514378e-05, "epoch": 1.4301675977653632, "percentage": 28.66, "elapsed_time": "0:43:45", "remaining_time": "1:48:56"} {"current_steps": 193, "total_steps": 670, "loss": 0.0197, "lr": 8.960812367055646e-05, "epoch": 1.4376163873370578, "percentage": 28.81, "elapsed_time": "0:43:59", "remaining_time": "1:48:42"} {"current_steps": 194, "total_steps": 670, "loss": 0.0193, "lr": 8.944860290709244e-05, "epoch": 1.4450651769087524, "percentage": 28.96, "elapsed_time": "0:44:12", "remaining_time": "1:48:28"} {"current_steps": 195, "total_steps": 670, "loss": 0.016, "lr": 8.928801137468654e-05, "epoch": 1.452513966480447, "percentage": 29.1, "elapsed_time": "0:44:26", "remaining_time": "1:48:15"} {"current_steps": 195, "total_steps": 670, "eval_loss": 0.017007919028401375, "epoch": 1.452513966480447, "percentage": 29.1, "elapsed_time": "0:44:28", "remaining_time": "1:48:19"} {"current_steps": 196, "total_steps": 670, "loss": 0.017, "lr": 8.912635343233784e-05, "epoch": 1.4599627560521415, "percentage": 29.25, "elapsed_time": "0:44:41", "remaining_time": "1:48:05"} {"current_steps": 197, "total_steps": 670, "loss": 0.0182, "lr": 8.896363346799146e-05, "epoch": 1.4674115456238361, "percentage": 29.4, "elapsed_time": "0:44:56", "remaining_time": "1:47:53"} {"current_steps": 198, "total_steps": 670, "loss": 0.0165, "lr": 8.879985589841937e-05, "epoch": 1.4748603351955307, "percentage": 29.55, "elapsed_time": "0:45:09", "remaining_time": "1:47:37"} {"current_steps": 199, "total_steps": 670, "loss": 0.0184, "lr": 8.863502516910058e-05, "epoch": 1.4823091247672253, "percentage": 29.7, "elapsed_time": "0:45:22", "remaining_time": "1:47:23"} {"current_steps": 200, "total_steps": 670, "loss": 0.0191, "lr": 8.846914575410034e-05, "epoch": 1.48975791433892, "percentage": 29.85, "elapsed_time": "0:45:38", "remaining_time": "1:47:15"} {"current_steps": 200, "total_steps": 670, "eval_loss": 0.016679175198078156, "epoch": 1.48975791433892, "percentage": 29.85, "elapsed_time": "0:45:39", "remaining_time": "1:47:18"} {"current_steps": 201, "total_steps": 670, "loss": 0.0154, "lr": 8.83022221559489e-05, "epoch": 1.4972067039106145, "percentage": 30.0, "elapsed_time": "0:45:55", "remaining_time": "1:47:08"} {"current_steps": 202, "total_steps": 670, "loss": 0.0177, "lr": 8.81342589055191e-05, "epoch": 1.504655493482309, "percentage": 30.15, "elapsed_time": "0:46:08", "remaining_time": "1:46:53"} {"current_steps": 203, "total_steps": 670, "loss": 0.0179, "lr": 8.79652605619035e-05, "epoch": 1.5121042830540037, "percentage": 30.3, "elapsed_time": "0:46:20", "remaining_time": "1:46:36"} {"current_steps": 204, "total_steps": 670, "loss": 0.016, "lr": 8.77952317122906e-05, "epoch": 1.5195530726256983, "percentage": 30.45, "elapsed_time": "0:46:35", "remaining_time": "1:46:25"} {"current_steps": 205, "total_steps": 670, "loss": 0.0186, "lr": 8.762417697184033e-05, "epoch": 1.5270018621973929, "percentage": 30.6, "elapsed_time": "0:46:48", "remaining_time": "1:46:09"} {"current_steps": 205, "total_steps": 670, "eval_loss": 0.016478266566991806, "epoch": 1.5270018621973929, "percentage": 30.6, "elapsed_time": "0:46:49", "remaining_time": "1:46:12"} {"current_steps": 206, "total_steps": 670, "loss": 0.0166, "lr": 8.745210098355878e-05, "epoch": 1.5344506517690877, "percentage": 30.75, "elapsed_time": "0:47:02", "remaining_time": "1:45:57"} {"current_steps": 207, "total_steps": 670, "loss": 0.0185, "lr": 8.727900841817215e-05, "epoch": 1.541899441340782, "percentage": 30.9, "elapsed_time": "0:47:14", "remaining_time": "1:45:40"} {"current_steps": 208, "total_steps": 670, "loss": 0.019, "lr": 8.710490397400006e-05, "epoch": 1.5493482309124769, "percentage": 31.04, "elapsed_time": "0:47:28", "remaining_time": "1:45:26"} {"current_steps": 209, "total_steps": 670, "loss": 0.0157, "lr": 8.692979237682786e-05, "epoch": 1.5567970204841712, "percentage": 31.19, "elapsed_time": "0:47:41", "remaining_time": "1:45:12"} {"current_steps": 210, "total_steps": 670, "loss": 0.0171, "lr": 8.675367837977849e-05, "epoch": 1.564245810055866, "percentage": 31.34, "elapsed_time": "0:47:55", "remaining_time": "1:44:59"} {"current_steps": 210, "total_steps": 670, "eval_loss": 0.01637791097164154, "epoch": 1.564245810055866, "percentage": 31.34, "elapsed_time": "0:47:57", "remaining_time": "1:45:02"} {"current_steps": 211, "total_steps": 670, "loss": 0.0173, "lr": 8.657656676318346e-05, "epoch": 1.5716945996275604, "percentage": 31.49, "elapsed_time": "0:48:11", "remaining_time": "1:44:49"} {"current_steps": 212, "total_steps": 670, "loss": 0.0173, "lr": 8.639846233445301e-05, "epoch": 1.5791433891992552, "percentage": 31.64, "elapsed_time": "0:48:26", "remaining_time": "1:44:39"} {"current_steps": 213, "total_steps": 670, "loss": 0.0187, "lr": 8.621936992794568e-05, "epoch": 1.5865921787709496, "percentage": 31.79, "elapsed_time": "0:48:39", "remaining_time": "1:44:23"} {"current_steps": 214, "total_steps": 670, "loss": 0.0189, "lr": 8.603929440483713e-05, "epoch": 1.5940409683426444, "percentage": 31.94, "elapsed_time": "0:48:52", "remaining_time": "1:44:08"} {"current_steps": 215, "total_steps": 670, "loss": 0.0192, "lr": 8.585824065298806e-05, "epoch": 1.6014897579143388, "percentage": 32.09, "elapsed_time": "0:49:05", "remaining_time": "1:43:53"} {"current_steps": 215, "total_steps": 670, "eval_loss": 0.016527703031897545, "epoch": 1.6014897579143388, "percentage": 32.09, "elapsed_time": "0:49:06", "remaining_time": "1:43:55"} {"current_steps": 216, "total_steps": 670, "loss": 0.0153, "lr": 8.567621358681165e-05, "epoch": 1.6089385474860336, "percentage": 32.24, "elapsed_time": "0:49:20", "remaining_time": "1:43:42"} {"current_steps": 217, "total_steps": 670, "loss": 0.0187, "lr": 8.549321814714018e-05, "epoch": 1.616387337057728, "percentage": 32.39, "elapsed_time": "0:49:32", "remaining_time": "1:43:26"} {"current_steps": 218, "total_steps": 670, "loss": 0.0159, "lr": 8.530925930109078e-05, "epoch": 1.6238361266294228, "percentage": 32.54, "elapsed_time": "0:49:45", "remaining_time": "1:43:10"} {"current_steps": 219, "total_steps": 670, "loss": 0.0157, "lr": 8.51243420419308e-05, "epoch": 1.6312849162011172, "percentage": 32.69, "elapsed_time": "0:49:59", "remaining_time": "1:42:57"} {"current_steps": 220, "total_steps": 670, "loss": 0.0154, "lr": 8.493847138894209e-05, "epoch": 1.638733705772812, "percentage": 32.84, "elapsed_time": "0:50:13", "remaining_time": "1:42:44"} {"current_steps": 220, "total_steps": 670, "eval_loss": 0.015912409871816635, "epoch": 1.638733705772812, "percentage": 32.84, "elapsed_time": "0:50:15", "remaining_time": "1:42:47"} {"current_steps": 221, "total_steps": 670, "loss": 0.0154, "lr": 8.475165238728489e-05, "epoch": 1.6461824953445066, "percentage": 32.99, "elapsed_time": "0:50:28", "remaining_time": "1:42:33"} {"current_steps": 222, "total_steps": 670, "loss": 0.0179, "lr": 8.456389010786083e-05, "epoch": 1.6536312849162011, "percentage": 33.13, "elapsed_time": "0:50:41", "remaining_time": "1:42:18"} {"current_steps": 223, "total_steps": 670, "loss": 0.0186, "lr": 8.43751896471753e-05, "epoch": 1.6610800744878957, "percentage": 33.28, "elapsed_time": "0:50:56", "remaining_time": "1:42:06"} {"current_steps": 224, "total_steps": 670, "loss": 0.018, "lr": 8.418555612719911e-05, "epoch": 1.6685288640595903, "percentage": 33.43, "elapsed_time": "0:51:07", "remaining_time": "1:41:48"} {"current_steps": 225, "total_steps": 670, "loss": 0.0179, "lr": 8.399499469522947e-05, "epoch": 1.675977653631285, "percentage": 33.58, "elapsed_time": "0:51:21", "remaining_time": "1:41:33"} {"current_steps": 225, "total_steps": 670, "eval_loss": 0.01597171649336815, "epoch": 1.675977653631285, "percentage": 33.58, "elapsed_time": "0:51:22", "remaining_time": "1:41:36"} {"current_steps": 226, "total_steps": 670, "loss": 0.019, "lr": 8.380351052375022e-05, "epoch": 1.6834264432029795, "percentage": 33.73, "elapsed_time": "0:51:34", "remaining_time": "1:41:20"} {"current_steps": 227, "total_steps": 670, "loss": 0.0174, "lr": 8.361110881029161e-05, "epoch": 1.690875232774674, "percentage": 33.88, "elapsed_time": "0:51:47", "remaining_time": "1:41:05"} {"current_steps": 228, "total_steps": 670, "loss": 0.016, "lr": 8.341779477728896e-05, "epoch": 1.6983240223463687, "percentage": 34.03, "elapsed_time": "0:52:02", "remaining_time": "1:40:52"} {"current_steps": 229, "total_steps": 670, "loss": 0.0169, "lr": 8.322357367194109e-05, "epoch": 1.7057728119180633, "percentage": 34.18, "elapsed_time": "0:52:15", "remaining_time": "1:40:37"} {"current_steps": 230, "total_steps": 670, "loss": 0.0153, "lr": 8.302845076606786e-05, "epoch": 1.7132216014897579, "percentage": 34.33, "elapsed_time": "0:52:28", "remaining_time": "1:40:23"} {"current_steps": 230, "total_steps": 670, "eval_loss": 0.015663128346204758, "epoch": 1.7132216014897579, "percentage": 34.33, "elapsed_time": "0:52:29", "remaining_time": "1:40:25"} {"current_steps": 231, "total_steps": 670, "loss": 0.0199, "lr": 8.283243135596701e-05, "epoch": 1.7206703910614525, "percentage": 34.48, "elapsed_time": "0:52:42", "remaining_time": "1:40:09"} {"current_steps": 232, "total_steps": 670, "loss": 0.0179, "lr": 8.263552076227048e-05, "epoch": 1.728119180633147, "percentage": 34.63, "elapsed_time": "0:52:55", "remaining_time": "1:39:55"} {"current_steps": 233, "total_steps": 670, "loss": 0.0167, "lr": 8.243772432979997e-05, "epoch": 1.7355679702048417, "percentage": 34.78, "elapsed_time": "0:53:09", "remaining_time": "1:39:41"} {"current_steps": 234, "total_steps": 670, "loss": 0.0198, "lr": 8.223904742742181e-05, "epoch": 1.7430167597765363, "percentage": 34.93, "elapsed_time": "0:53:22", "remaining_time": "1:39:26"} {"current_steps": 235, "total_steps": 670, "loss": 0.0162, "lr": 8.203949544790131e-05, "epoch": 1.750465549348231, "percentage": 35.07, "elapsed_time": "0:53:34", "remaining_time": "1:39:10"} {"current_steps": 235, "total_steps": 670, "eval_loss": 0.015515139326453209, "epoch": 1.750465549348231, "percentage": 35.07, "elapsed_time": "0:53:36", "remaining_time": "1:39:13"} {"current_steps": 236, "total_steps": 670, "loss": 0.0179, "lr": 8.183907380775631e-05, "epoch": 1.7579143389199254, "percentage": 35.22, "elapsed_time": "0:53:49", "remaining_time": "1:38:59"} {"current_steps": 237, "total_steps": 670, "loss": 0.0173, "lr": 8.163778794711019e-05, "epoch": 1.7653631284916202, "percentage": 35.37, "elapsed_time": "0:54:03", "remaining_time": "1:38:45"} {"current_steps": 238, "total_steps": 670, "loss": 0.0142, "lr": 8.143564332954425e-05, "epoch": 1.7728119180633146, "percentage": 35.52, "elapsed_time": "0:54:16", "remaining_time": "1:38:31"} {"current_steps": 239, "total_steps": 670, "loss": 0.0167, "lr": 8.123264544194933e-05, "epoch": 1.7802607076350094, "percentage": 35.67, "elapsed_time": "0:54:30", "remaining_time": "1:38:17"} {"current_steps": 240, "total_steps": 670, "loss": 0.0166, "lr": 8.10287997943769e-05, "epoch": 1.7877094972067038, "percentage": 35.82, "elapsed_time": "0:54:42", "remaining_time": "1:38:01"} {"current_steps": 240, "total_steps": 670, "eval_loss": 0.015411162748932838, "epoch": 1.7877094972067038, "percentage": 35.82, "elapsed_time": "0:54:44", "remaining_time": "1:38:04"} {"current_steps": 241, "total_steps": 670, "loss": 0.0167, "lr": 8.082411191988957e-05, "epoch": 1.7951582867783986, "percentage": 35.97, "elapsed_time": "0:54:57", "remaining_time": "1:37:49"} {"current_steps": 242, "total_steps": 670, "loss": 0.0145, "lr": 8.061858737441078e-05, "epoch": 1.802607076350093, "percentage": 36.12, "elapsed_time": "0:55:10", "remaining_time": "1:37:35"} {"current_steps": 243, "total_steps": 670, "loss": 0.0153, "lr": 8.04122317365741e-05, "epoch": 1.8100558659217878, "percentage": 36.27, "elapsed_time": "0:55:24", "remaining_time": "1:37:21"} {"current_steps": 244, "total_steps": 670, "loss": 0.0163, "lr": 8.020505060757179e-05, "epoch": 1.8175046554934822, "percentage": 36.42, "elapsed_time": "0:55:37", "remaining_time": "1:37:07"} {"current_steps": 245, "total_steps": 670, "loss": 0.0147, "lr": 7.999704961100266e-05, "epoch": 1.824953445065177, "percentage": 36.57, "elapsed_time": "0:55:51", "remaining_time": "1:36:54"} {"current_steps": 245, "total_steps": 670, "eval_loss": 0.015263408422470093, "epoch": 1.824953445065177, "percentage": 36.57, "elapsed_time": "0:55:53", "remaining_time": "1:36:56"} {"current_steps": 246, "total_steps": 670, "loss": 0.0145, "lr": 7.978823439271958e-05, "epoch": 1.8324022346368714, "percentage": 36.72, "elapsed_time": "0:56:05", "remaining_time": "1:36:40"} {"current_steps": 247, "total_steps": 670, "loss": 0.0158, "lr": 7.957861062067614e-05, "epoch": 1.8398510242085662, "percentage": 36.87, "elapsed_time": "0:56:19", "remaining_time": "1:36:27"} {"current_steps": 248, "total_steps": 670, "loss": 0.0142, "lr": 7.936818398477279e-05, "epoch": 1.8472998137802608, "percentage": 37.01, "elapsed_time": "0:56:33", "remaining_time": "1:36:14"} {"current_steps": 249, "total_steps": 670, "loss": 0.0194, "lr": 7.915696019670249e-05, "epoch": 1.8547486033519553, "percentage": 37.16, "elapsed_time": "0:56:46", "remaining_time": "1:35:59"} {"current_steps": 250, "total_steps": 670, "loss": 0.016, "lr": 7.894494498979557e-05, "epoch": 1.86219739292365, "percentage": 37.31, "elapsed_time": "0:57:00", "remaining_time": "1:35:46"} {"current_steps": 250, "total_steps": 670, "eval_loss": 0.015286728739738464, "epoch": 1.86219739292365, "percentage": 37.31, "elapsed_time": "0:57:01", "remaining_time": "1:35:48"} {"current_steps": 251, "total_steps": 670, "loss": 0.015, "lr": 7.873214411886419e-05, "epoch": 1.8696461824953445, "percentage": 37.46, "elapsed_time": "0:57:16", "remaining_time": "1:35:36"} {"current_steps": 252, "total_steps": 670, "loss": 0.0172, "lr": 7.851856336004604e-05, "epoch": 1.8770949720670391, "percentage": 37.61, "elapsed_time": "0:57:29", "remaining_time": "1:35:21"} {"current_steps": 253, "total_steps": 670, "loss": 0.0164, "lr": 7.830420851064766e-05, "epoch": 1.8845437616387337, "percentage": 37.76, "elapsed_time": "0:57:42", "remaining_time": "1:35:07"} {"current_steps": 254, "total_steps": 670, "loss": 0.0156, "lr": 7.808908538898702e-05, "epoch": 1.8919925512104283, "percentage": 37.91, "elapsed_time": "0:57:54", "remaining_time": "1:34:51"} {"current_steps": 255, "total_steps": 670, "loss": 0.0153, "lr": 7.787319983423563e-05, "epoch": 1.899441340782123, "percentage": 38.06, "elapsed_time": "0:58:08", "remaining_time": "1:34:37"} {"current_steps": 255, "total_steps": 670, "eval_loss": 0.014994229190051556, "epoch": 1.899441340782123, "percentage": 38.06, "elapsed_time": "0:58:10", "remaining_time": "1:34:39"} {"current_steps": 256, "total_steps": 670, "loss": 0.0156, "lr": 7.765655770625997e-05, "epoch": 1.9068901303538175, "percentage": 38.21, "elapsed_time": "0:58:22", "remaining_time": "1:34:24"} {"current_steps": 257, "total_steps": 670, "loss": 0.0155, "lr": 7.743916488546254e-05, "epoch": 1.914338919925512, "percentage": 38.36, "elapsed_time": "0:58:36", "remaining_time": "1:34:11"} {"current_steps": 258, "total_steps": 670, "loss": 0.015, "lr": 7.722102727262215e-05, "epoch": 1.9217877094972067, "percentage": 38.51, "elapsed_time": "0:58:49", "remaining_time": "1:33:56"} {"current_steps": 259, "total_steps": 670, "loss": 0.0141, "lr": 7.700215078873379e-05, "epoch": 1.9292364990689013, "percentage": 38.66, "elapsed_time": "0:59:03", "remaining_time": "1:33:43"} {"current_steps": 260, "total_steps": 670, "loss": 0.0157, "lr": 7.678254137484797e-05, "epoch": 1.9366852886405959, "percentage": 38.81, "elapsed_time": "0:59:17", "remaining_time": "1:33:29"} {"current_steps": 260, "total_steps": 670, "eval_loss": 0.014934035018086433, "epoch": 1.9366852886405959, "percentage": 38.81, "elapsed_time": "0:59:18", "remaining_time": "1:33:31"} {"current_steps": 261, "total_steps": 670, "loss": 0.0169, "lr": 7.656220499190936e-05, "epoch": 1.9441340782122905, "percentage": 38.96, "elapsed_time": "0:59:31", "remaining_time": "1:33:17"} {"current_steps": 262, "total_steps": 670, "loss": 0.0192, "lr": 7.634114762059504e-05, "epoch": 1.9515828677839853, "percentage": 39.1, "elapsed_time": "0:59:45", "remaining_time": "1:33:03"} {"current_steps": 263, "total_steps": 670, "loss": 0.0134, "lr": 7.611937526115218e-05, "epoch": 1.9590316573556796, "percentage": 39.25, "elapsed_time": "0:59:58", "remaining_time": "1:32:49"} {"current_steps": 264, "total_steps": 670, "loss": 0.0165, "lr": 7.589689393323514e-05, "epoch": 1.9664804469273744, "percentage": 39.4, "elapsed_time": "1:00:11", "remaining_time": "1:32:34"} {"current_steps": 265, "total_steps": 670, "loss": 0.0165, "lr": 7.56737096757421e-05, "epoch": 1.9739292364990688, "percentage": 39.55, "elapsed_time": "1:00:24", "remaining_time": "1:32:19"} {"current_steps": 265, "total_steps": 670, "eval_loss": 0.014995547011494637, "epoch": 1.9739292364990688, "percentage": 39.55, "elapsed_time": "1:00:25", "remaining_time": "1:32:21"} {"current_steps": 266, "total_steps": 670, "loss": 0.0163, "lr": 7.544982854665113e-05, "epoch": 1.9813780260707636, "percentage": 39.7, "elapsed_time": "1:00:38", "remaining_time": "1:32:05"} {"current_steps": 267, "total_steps": 670, "loss": 0.017, "lr": 7.522525662285575e-05, "epoch": 1.988826815642458, "percentage": 39.85, "elapsed_time": "1:00:51", "remaining_time": "1:31:51"} {"current_steps": 268, "total_steps": 670, "loss": 0.0165, "lr": 7.500000000000001e-05, "epoch": 1.9962756052141528, "percentage": 40.0, "elapsed_time": "1:01:04", "remaining_time": "1:31:37"} {"current_steps": 269, "total_steps": 670, "loss": 0.0277, "lr": 7.4774064792313e-05, "epoch": 2.003724394785847, "percentage": 40.15, "elapsed_time": "1:01:18", "remaining_time": "1:31:24"} {"current_steps": 270, "total_steps": 670, "loss": 0.0153, "lr": 7.454745713244289e-05, "epoch": 2.011173184357542, "percentage": 40.3, "elapsed_time": "1:01:32", "remaining_time": "1:31:09"} {"current_steps": 270, "total_steps": 670, "eval_loss": 0.014832735061645508, "epoch": 2.011173184357542, "percentage": 40.3, "elapsed_time": "1:01:33", "remaining_time": "1:31:11"} {"current_steps": 271, "total_steps": 670, "loss": 0.0145, "lr": 7.432018317129056e-05, "epoch": 2.0186219739292364, "percentage": 40.45, "elapsed_time": "1:01:46", "remaining_time": "1:30:57"} {"current_steps": 272, "total_steps": 670, "loss": 0.0164, "lr": 7.409224907784247e-05, "epoch": 2.026070763500931, "percentage": 40.6, "elapsed_time": "1:02:00", "remaining_time": "1:30:43"} {"current_steps": 273, "total_steps": 670, "loss": 0.0164, "lr": 7.386366103900337e-05, "epoch": 2.0335195530726256, "percentage": 40.75, "elapsed_time": "1:02:13", "remaining_time": "1:30:29"} {"current_steps": 274, "total_steps": 670, "loss": 0.0174, "lr": 7.363442525942826e-05, "epoch": 2.0409683426443204, "percentage": 40.9, "elapsed_time": "1:02:27", "remaining_time": "1:30:16"} {"current_steps": 275, "total_steps": 670, "loss": 0.015, "lr": 7.34045479613541e-05, "epoch": 2.0484171322160147, "percentage": 41.04, "elapsed_time": "1:02:42", "remaining_time": "1:30:03"} {"current_steps": 275, "total_steps": 670, "eval_loss": 0.01486313808709383, "epoch": 2.0484171322160147, "percentage": 41.04, "elapsed_time": "1:02:43", "remaining_time": "1:30:05"} {"current_steps": 276, "total_steps": 670, "loss": 0.0131, "lr": 7.317403538443078e-05, "epoch": 2.0558659217877095, "percentage": 41.19, "elapsed_time": "1:02:56", "remaining_time": "1:29:51"} {"current_steps": 277, "total_steps": 670, "loss": 0.014, "lr": 7.294289378555179e-05, "epoch": 2.063314711359404, "percentage": 41.34, "elapsed_time": "1:03:08", "remaining_time": "1:29:34"} {"current_steps": 278, "total_steps": 670, "loss": 0.0145, "lr": 7.271112943868448e-05, "epoch": 2.0707635009310987, "percentage": 41.49, "elapsed_time": "1:03:21", "remaining_time": "1:29:20"} {"current_steps": 279, "total_steps": 670, "loss": 0.0152, "lr": 7.247874863469964e-05, "epoch": 2.078212290502793, "percentage": 41.64, "elapsed_time": "1:03:34", "remaining_time": "1:29:05"} {"current_steps": 280, "total_steps": 670, "loss": 0.0159, "lr": 7.224575768120083e-05, "epoch": 2.085661080074488, "percentage": 41.79, "elapsed_time": "1:03:49", "remaining_time": "1:28:53"} {"current_steps": 280, "total_steps": 670, "eval_loss": 0.01477406732738018, "epoch": 2.085661080074488, "percentage": 41.79, "elapsed_time": "1:03:50", "remaining_time": "1:28:55"} {"current_steps": 281, "total_steps": 670, "loss": 0.0136, "lr": 7.201216290235312e-05, "epoch": 2.0931098696461823, "percentage": 41.94, "elapsed_time": "1:04:02", "remaining_time": "1:28:39"} {"current_steps": 282, "total_steps": 670, "loss": 0.0163, "lr": 7.177797063871146e-05, "epoch": 2.100558659217877, "percentage": 42.09, "elapsed_time": "1:04:16", "remaining_time": "1:28:26"} {"current_steps": 283, "total_steps": 670, "loss": 0.0133, "lr": 7.154318724704853e-05, "epoch": 2.1080074487895715, "percentage": 42.24, "elapsed_time": "1:04:31", "remaining_time": "1:28:14"} {"current_steps": 284, "total_steps": 670, "loss": 0.0169, "lr": 7.130781910018227e-05, "epoch": 2.1154562383612663, "percentage": 42.39, "elapsed_time": "1:04:45", "remaining_time": "1:28:00"} {"current_steps": 285, "total_steps": 670, "loss": 0.0166, "lr": 7.107187258680287e-05, "epoch": 2.122905027932961, "percentage": 42.54, "elapsed_time": "1:04:57", "remaining_time": "1:27:44"} {"current_steps": 285, "total_steps": 670, "eval_loss": 0.014633920043706894, "epoch": 2.122905027932961, "percentage": 42.54, "elapsed_time": "1:04:58", "remaining_time": "1:27:46"} {"current_steps": 286, "total_steps": 670, "loss": 0.0137, "lr": 7.083535411129933e-05, "epoch": 2.1303538175046555, "percentage": 42.69, "elapsed_time": "1:05:11", "remaining_time": "1:27:31"} {"current_steps": 287, "total_steps": 670, "loss": 0.0161, "lr": 7.059827009358563e-05, "epoch": 2.1378026070763503, "percentage": 42.84, "elapsed_time": "1:05:24", "remaining_time": "1:27:17"} {"current_steps": 288, "total_steps": 670, "loss": 0.0142, "lr": 7.036062696892648e-05, "epoch": 2.1452513966480447, "percentage": 42.99, "elapsed_time": "1:05:39", "remaining_time": "1:27:04"} {"current_steps": 289, "total_steps": 670, "loss": 0.013, "lr": 7.012243118776269e-05, "epoch": 2.1527001862197395, "percentage": 43.13, "elapsed_time": "1:05:52", "remaining_time": "1:26:50"} {"current_steps": 290, "total_steps": 670, "loss": 0.0153, "lr": 6.988368921553601e-05, "epoch": 2.160148975791434, "percentage": 43.28, "elapsed_time": "1:06:06", "remaining_time": "1:26:37"} {"current_steps": 290, "total_steps": 670, "eval_loss": 0.014632484875619411, "epoch": 2.160148975791434, "percentage": 43.28, "elapsed_time": "1:06:07", "remaining_time": "1:26:39"} {"current_steps": 291, "total_steps": 670, "loss": 0.0145, "lr": 6.964440753251366e-05, "epoch": 2.1675977653631286, "percentage": 43.43, "elapsed_time": "1:06:21", "remaining_time": "1:26:25"} {"current_steps": 292, "total_steps": 670, "loss": 0.0137, "lr": 6.940459263361249e-05, "epoch": 2.175046554934823, "percentage": 43.58, "elapsed_time": "1:06:34", "remaining_time": "1:26:10"} {"current_steps": 293, "total_steps": 670, "loss": 0.0149, "lr": 6.91642510282226e-05, "epoch": 2.182495344506518, "percentage": 43.73, "elapsed_time": "1:06:47", "remaining_time": "1:25:56"} {"current_steps": 294, "total_steps": 670, "loss": 0.0185, "lr": 6.892338924003067e-05, "epoch": 2.189944134078212, "percentage": 43.88, "elapsed_time": "1:07:00", "remaining_time": "1:25:42"} {"current_steps": 295, "total_steps": 670, "loss": 0.013, "lr": 6.868201380684299e-05, "epoch": 2.197392923649907, "percentage": 44.03, "elapsed_time": "1:07:14", "remaining_time": "1:25:28"} {"current_steps": 295, "total_steps": 670, "eval_loss": 0.014326302334666252, "epoch": 2.197392923649907, "percentage": 44.03, "elapsed_time": "1:07:15", "remaining_time": "1:25:30"} {"current_steps": 296, "total_steps": 670, "loss": 0.0145, "lr": 6.844013128040782e-05, "epoch": 2.2048417132216014, "percentage": 44.18, "elapsed_time": "1:07:29", "remaining_time": "1:25:16"} {"current_steps": 297, "total_steps": 670, "loss": 0.0145, "lr": 6.819774822623772e-05, "epoch": 2.212290502793296, "percentage": 44.33, "elapsed_time": "1:07:43", "remaining_time": "1:25:02"} {"current_steps": 298, "total_steps": 670, "loss": 0.0175, "lr": 6.795487122343124e-05, "epoch": 2.2197392923649906, "percentage": 44.48, "elapsed_time": "1:07:56", "remaining_time": "1:24:48"} {"current_steps": 299, "total_steps": 670, "loss": 0.0155, "lr": 6.771150686449436e-05, "epoch": 2.2271880819366854, "percentage": 44.63, "elapsed_time": "1:08:10", "remaining_time": "1:24:35"} {"current_steps": 300, "total_steps": 670, "loss": 0.0139, "lr": 6.74676617551616e-05, "epoch": 2.2346368715083798, "percentage": 44.78, "elapsed_time": "1:08:23", "remaining_time": "1:24:20"} {"current_steps": 300, "total_steps": 670, "eval_loss": 0.014321574941277504, "epoch": 2.2346368715083798, "percentage": 44.78, "elapsed_time": "1:08:24", "remaining_time": "1:24:22"} {"current_steps": 301, "total_steps": 670, "loss": 0.0141, "lr": 6.722334251421665e-05, "epoch": 2.2420856610800746, "percentage": 44.93, "elapsed_time": "1:08:38", "remaining_time": "1:24:09"} {"current_steps": 302, "total_steps": 670, "loss": 0.0146, "lr": 6.697855577331274e-05, "epoch": 2.249534450651769, "percentage": 45.07, "elapsed_time": "1:08:52", "remaining_time": "1:23:55"} {"current_steps": 303, "total_steps": 670, "loss": 0.016, "lr": 6.673330817679265e-05, "epoch": 2.2569832402234637, "percentage": 45.22, "elapsed_time": "1:09:04", "remaining_time": "1:23:39"} {"current_steps": 304, "total_steps": 670, "loss": 0.0133, "lr": 6.648760638150832e-05, "epoch": 2.264432029795158, "percentage": 45.37, "elapsed_time": "1:09:16", "remaining_time": "1:23:24"} {"current_steps": 305, "total_steps": 670, "loss": 0.016, "lr": 6.624145705664023e-05, "epoch": 2.271880819366853, "percentage": 45.52, "elapsed_time": "1:09:30", "remaining_time": "1:23:10"} {"current_steps": 305, "total_steps": 670, "eval_loss": 0.01447533629834652, "epoch": 2.271880819366853, "percentage": 45.52, "elapsed_time": "1:09:31", "remaining_time": "1:23:12"} {"current_steps": 306, "total_steps": 670, "loss": 0.0128, "lr": 6.599486688351628e-05, "epoch": 2.2793296089385473, "percentage": 45.67, "elapsed_time": "1:09:44", "remaining_time": "1:22:57"} {"current_steps": 307, "total_steps": 670, "loss": 0.0146, "lr": 6.574784255543051e-05, "epoch": 2.286778398510242, "percentage": 45.82, "elapsed_time": "1:09:58", "remaining_time": "1:22:44"} {"current_steps": 308, "total_steps": 670, "loss": 0.014, "lr": 6.550039077746142e-05, "epoch": 2.294227188081937, "percentage": 45.97, "elapsed_time": "1:10:12", "remaining_time": "1:22:30"} {"current_steps": 309, "total_steps": 670, "loss": 0.0151, "lr": 6.525251826628991e-05, "epoch": 2.3016759776536313, "percentage": 46.12, "elapsed_time": "1:10:26", "remaining_time": "1:22:17"} {"current_steps": 310, "total_steps": 670, "loss": 0.0142, "lr": 6.500423175001705e-05, "epoch": 2.3091247672253257, "percentage": 46.27, "elapsed_time": "1:10:39", "remaining_time": "1:22:03"} {"current_steps": 310, "total_steps": 670, "eval_loss": 0.014361077919602394, "epoch": 2.3091247672253257, "percentage": 46.27, "elapsed_time": "1:10:40", "remaining_time": "1:22:04"} {"current_steps": 311, "total_steps": 670, "loss": 0.0132, "lr": 6.475553796798135e-05, "epoch": 2.3165735567970205, "percentage": 46.42, "elapsed_time": "1:10:54", "remaining_time": "1:21:51"} {"current_steps": 312, "total_steps": 670, "loss": 0.0134, "lr": 6.450644367057597e-05, "epoch": 2.3240223463687153, "percentage": 46.57, "elapsed_time": "1:11:07", "remaining_time": "1:21:36"} {"current_steps": 313, "total_steps": 670, "loss": 0.0142, "lr": 6.425695561906537e-05, "epoch": 2.3314711359404097, "percentage": 46.72, "elapsed_time": "1:11:20", "remaining_time": "1:21:22"} {"current_steps": 314, "total_steps": 670, "loss": 0.014, "lr": 6.400708058540182e-05, "epoch": 2.338919925512104, "percentage": 46.87, "elapsed_time": "1:11:34", "remaining_time": "1:21:08"} {"current_steps": 315, "total_steps": 670, "loss": 0.0138, "lr": 6.375682535204167e-05, "epoch": 2.346368715083799, "percentage": 47.01, "elapsed_time": "1:11:46", "remaining_time": "1:20:53"} {"current_steps": 315, "total_steps": 670, "eval_loss": 0.014339178800582886, "epoch": 2.346368715083799, "percentage": 47.01, "elapsed_time": "1:11:48", "remaining_time": "1:20:55"} {"current_steps": 316, "total_steps": 670, "loss": 0.0132, "lr": 6.350619671176111e-05, "epoch": 2.3538175046554937, "percentage": 47.16, "elapsed_time": "1:12:02", "remaining_time": "1:20:41"} {"current_steps": 317, "total_steps": 670, "loss": 0.0161, "lr": 6.325520146747189e-05, "epoch": 2.361266294227188, "percentage": 47.31, "elapsed_time": "1:12:16", "remaining_time": "1:20:28"} {"current_steps": 318, "total_steps": 670, "loss": 0.0142, "lr": 6.30038464320366e-05, "epoch": 2.368715083798883, "percentage": 47.46, "elapsed_time": "1:12:29", "remaining_time": "1:20:14"} {"current_steps": 319, "total_steps": 670, "loss": 0.0141, "lr": 6.275213842808383e-05, "epoch": 2.376163873370577, "percentage": 47.61, "elapsed_time": "1:12:44", "remaining_time": "1:20:01"} {"current_steps": 320, "total_steps": 670, "loss": 0.0151, "lr": 6.250008428782292e-05, "epoch": 2.383612662942272, "percentage": 47.76, "elapsed_time": "1:12:57", "remaining_time": "1:19:47"} {"current_steps": 320, "total_steps": 670, "eval_loss": 0.014254897832870483, "epoch": 2.383612662942272, "percentage": 47.76, "elapsed_time": "1:12:59", "remaining_time": "1:19:49"} {"current_steps": 321, "total_steps": 670, "loss": 0.0133, "lr": 6.224769085285854e-05, "epoch": 2.3910614525139664, "percentage": 47.91, "elapsed_time": "1:13:12", "remaining_time": "1:19:35"} {"current_steps": 322, "total_steps": 670, "loss": 0.0152, "lr": 6.19949649740049e-05, "epoch": 2.398510242085661, "percentage": 48.06, "elapsed_time": "1:13:25", "remaining_time": "1:19:21"} {"current_steps": 323, "total_steps": 670, "loss": 0.0131, "lr": 6.174191351109995e-05, "epoch": 2.4059590316573556, "percentage": 48.21, "elapsed_time": "1:13:38", "remaining_time": "1:19:07"} {"current_steps": 324, "total_steps": 670, "loss": 0.0147, "lr": 6.148854333281905e-05, "epoch": 2.4134078212290504, "percentage": 48.36, "elapsed_time": "1:13:53", "remaining_time": "1:18:54"} {"current_steps": 325, "total_steps": 670, "loss": 0.0152, "lr": 6.12348613164886e-05, "epoch": 2.4208566108007448, "percentage": 48.51, "elapsed_time": "1:14:05", "remaining_time": "1:18:39"} {"current_steps": 325, "total_steps": 670, "eval_loss": 0.014044879004359245, "epoch": 2.4208566108007448, "percentage": 48.51, "elapsed_time": "1:14:07", "remaining_time": "1:18:40"} {"current_steps": 326, "total_steps": 670, "loss": 0.0141, "lr": 6.098087434789931e-05, "epoch": 2.4283054003724396, "percentage": 48.66, "elapsed_time": "1:14:20", "remaining_time": "1:18:27"} {"current_steps": 327, "total_steps": 670, "loss": 0.0153, "lr": 6.0726589321119364e-05, "epoch": 2.435754189944134, "percentage": 48.81, "elapsed_time": "1:14:33", "remaining_time": "1:18:12"} {"current_steps": 328, "total_steps": 670, "loss": 0.0159, "lr": 6.0472013138307235e-05, "epoch": 2.4432029795158288, "percentage": 48.96, "elapsed_time": "1:14:47", "remaining_time": "1:17:58"} {"current_steps": 329, "total_steps": 670, "loss": 0.0147, "lr": 6.021715270952435e-05, "epoch": 2.450651769087523, "percentage": 49.1, "elapsed_time": "1:15:00", "remaining_time": "1:17:44"} {"current_steps": 330, "total_steps": 670, "loss": 0.0141, "lr": 5.9962014952547575e-05, "epoch": 2.458100558659218, "percentage": 49.25, "elapsed_time": "1:15:13", "remaining_time": "1:17:30"} {"current_steps": 330, "total_steps": 670, "eval_loss": 0.014173776842653751, "epoch": 2.458100558659218, "percentage": 49.25, "elapsed_time": "1:15:14", "remaining_time": "1:17:31"} {"current_steps": 331, "total_steps": 670, "loss": 0.0129, "lr": 5.970660679268138e-05, "epoch": 2.4655493482309123, "percentage": 49.4, "elapsed_time": "1:15:28", "remaining_time": "1:17:17"} {"current_steps": 332, "total_steps": 670, "loss": 0.0154, "lr": 5.945093516256989e-05, "epoch": 2.472998137802607, "percentage": 49.55, "elapsed_time": "1:15:40", "remaining_time": "1:17:02"} {"current_steps": 333, "total_steps": 670, "loss": 0.0143, "lr": 5.9195007002008685e-05, "epoch": 2.4804469273743015, "percentage": 49.7, "elapsed_time": "1:15:54", "remaining_time": "1:16:49"} {"current_steps": 334, "total_steps": 670, "loss": 0.0178, "lr": 5.893882925775648e-05, "epoch": 2.4878957169459963, "percentage": 49.85, "elapsed_time": "1:16:07", "remaining_time": "1:16:34"} {"current_steps": 335, "total_steps": 670, "loss": 0.0137, "lr": 5.868240888334653e-05, "epoch": 2.4953445065176907, "percentage": 50.0, "elapsed_time": "1:16:21", "remaining_time": "1:16:21"} {"current_steps": 335, "total_steps": 670, "eval_loss": 0.013938896358013153, "epoch": 2.4953445065176907, "percentage": 50.0, "elapsed_time": "1:16:22", "remaining_time": "1:16:22"} {"current_steps": 336, "total_steps": 670, "loss": 0.0131, "lr": 5.842575283889789e-05, "epoch": 2.5027932960893855, "percentage": 50.15, "elapsed_time": "1:16:36", "remaining_time": "1:16:09"} {"current_steps": 337, "total_steps": 670, "loss": 0.0187, "lr": 5.816886809092651e-05, "epoch": 2.51024208566108, "percentage": 50.3, "elapsed_time": "1:16:50", "remaining_time": "1:15:55"} {"current_steps": 338, "total_steps": 670, "loss": 0.0126, "lr": 5.7911761612156135e-05, "epoch": 2.5176908752327747, "percentage": 50.45, "elapsed_time": "1:17:03", "remaining_time": "1:15:41"} {"current_steps": 339, "total_steps": 670, "loss": 0.0156, "lr": 5.765444038132901e-05, "epoch": 2.5251396648044695, "percentage": 50.6, "elapsed_time": "1:17:16", "remaining_time": "1:15:27"} {"current_steps": 340, "total_steps": 670, "loss": 0.0132, "lr": 5.73969113830165e-05, "epoch": 2.532588454376164, "percentage": 50.75, "elapsed_time": "1:17:30", "remaining_time": "1:15:13"} {"current_steps": 340, "total_steps": 670, "eval_loss": 0.013844965025782585, "epoch": 2.532588454376164, "percentage": 50.75, "elapsed_time": "1:17:31", "remaining_time": "1:15:15"} {"current_steps": 341, "total_steps": 670, "loss": 0.0178, "lr": 5.713918160742948e-05, "epoch": 2.5400372439478582, "percentage": 50.9, "elapsed_time": "1:17:44", "remaining_time": "1:15:00"} {"current_steps": 342, "total_steps": 670, "loss": 0.0135, "lr": 5.688125805022861e-05, "epoch": 2.547486033519553, "percentage": 51.04, "elapsed_time": "1:17:58", "remaining_time": "1:14:46"} {"current_steps": 343, "total_steps": 670, "loss": 0.0156, "lr": 5.66231477123344e-05, "epoch": 2.554934823091248, "percentage": 51.19, "elapsed_time": "1:18:12", "remaining_time": "1:14:33"} {"current_steps": 344, "total_steps": 670, "loss": 0.0127, "lr": 5.636485759973729e-05, "epoch": 2.5623836126629422, "percentage": 51.34, "elapsed_time": "1:18:26", "remaining_time": "1:14:20"} {"current_steps": 345, "total_steps": 670, "loss": 0.0132, "lr": 5.6106394723307365e-05, "epoch": 2.5698324022346366, "percentage": 51.49, "elapsed_time": "1:18:40", "remaining_time": "1:14:06"} {"current_steps": 345, "total_steps": 670, "eval_loss": 0.013647645711898804, "epoch": 2.5698324022346366, "percentage": 51.49, "elapsed_time": "1:18:41", "remaining_time": "1:14:07"} {"current_steps": 346, "total_steps": 670, "loss": 0.0164, "lr": 5.584776609860414e-05, "epoch": 2.5772811918063314, "percentage": 51.64, "elapsed_time": "1:18:54", "remaining_time": "1:13:53"} {"current_steps": 347, "total_steps": 670, "loss": 0.0122, "lr": 5.558897874568604e-05, "epoch": 2.5847299813780262, "percentage": 51.79, "elapsed_time": "1:19:07", "remaining_time": "1:13:39"} {"current_steps": 348, "total_steps": 670, "loss": 0.0135, "lr": 5.533003968891998e-05, "epoch": 2.5921787709497206, "percentage": 51.94, "elapsed_time": "1:19:21", "remaining_time": "1:13:25"} {"current_steps": 349, "total_steps": 670, "loss": 0.0122, "lr": 5.5070955956790594e-05, "epoch": 2.5996275605214154, "percentage": 52.09, "elapsed_time": "1:19:33", "remaining_time": "1:13:10"} {"current_steps": 350, "total_steps": 670, "loss": 0.0162, "lr": 5.4811734581709514e-05, "epoch": 2.60707635009311, "percentage": 52.24, "elapsed_time": "1:19:46", "remaining_time": "1:12:56"} {"current_steps": 350, "total_steps": 670, "eval_loss": 0.013542103581130505, "epoch": 2.60707635009311, "percentage": 52.24, "elapsed_time": "1:19:47", "remaining_time": "1:12:57"} {"current_steps": 351, "total_steps": 670, "loss": 0.0167, "lr": 5.455238259982448e-05, "epoch": 2.6145251396648046, "percentage": 52.39, "elapsed_time": "1:20:01", "remaining_time": "1:12:43"} {"current_steps": 352, "total_steps": 670, "loss": 0.0151, "lr": 5.42929070508283e-05, "epoch": 2.621973929236499, "percentage": 52.54, "elapsed_time": "1:20:14", "remaining_time": "1:12:29"} {"current_steps": 353, "total_steps": 670, "loss": 0.0125, "lr": 5.4033314977767856e-05, "epoch": 2.629422718808194, "percentage": 52.69, "elapsed_time": "1:20:26", "remaining_time": "1:12:14"} {"current_steps": 354, "total_steps": 670, "loss": 0.0135, "lr": 5.377361342685287e-05, "epoch": 2.636871508379888, "percentage": 52.84, "elapsed_time": "1:20:39", "remaining_time": "1:11:59"} {"current_steps": 355, "total_steps": 670, "loss": 0.0133, "lr": 5.351380944726465e-05, "epoch": 2.644320297951583, "percentage": 52.99, "elapsed_time": "1:20:52", "remaining_time": "1:11:45"} {"current_steps": 355, "total_steps": 670, "eval_loss": 0.013467466458678246, "epoch": 2.644320297951583, "percentage": 52.99, "elapsed_time": "1:20:53", "remaining_time": "1:11:46"} {"current_steps": 356, "total_steps": 670, "loss": 0.0159, "lr": 5.325391009096481e-05, "epoch": 2.6517690875232773, "percentage": 53.13, "elapsed_time": "1:21:07", "remaining_time": "1:11:32"} {"current_steps": 357, "total_steps": 670, "loss": 0.0129, "lr": 5.299392241250376e-05, "epoch": 2.659217877094972, "percentage": 53.28, "elapsed_time": "1:21:20", "remaining_time": "1:11:18"} {"current_steps": 358, "total_steps": 670, "loss": 0.0135, "lr": 5.27338534688293e-05, "epoch": 2.6666666666666665, "percentage": 53.43, "elapsed_time": "1:21:33", "remaining_time": "1:11:04"} {"current_steps": 359, "total_steps": 670, "loss": 0.0122, "lr": 5.247371031909505e-05, "epoch": 2.6741154562383613, "percentage": 53.58, "elapsed_time": "1:21:47", "remaining_time": "1:10:51"} {"current_steps": 360, "total_steps": 670, "loss": 0.0134, "lr": 5.221350002446882e-05, "epoch": 2.6815642458100557, "percentage": 53.73, "elapsed_time": "1:22:00", "remaining_time": "1:10:37"} {"current_steps": 360, "total_steps": 670, "eval_loss": 0.013446934521198273, "epoch": 2.6815642458100557, "percentage": 53.73, "elapsed_time": "1:22:02", "remaining_time": "1:10:38"} {"current_steps": 361, "total_steps": 670, "loss": 0.0141, "lr": 5.195322964794098e-05, "epoch": 2.6890130353817505, "percentage": 53.88, "elapsed_time": "1:22:16", "remaining_time": "1:10:25"} {"current_steps": 362, "total_steps": 670, "loss": 0.0149, "lr": 5.169290625413268e-05, "epoch": 2.6964618249534453, "percentage": 54.03, "elapsed_time": "1:22:29", "remaining_time": "1:10:11"} {"current_steps": 363, "total_steps": 670, "loss": 0.0166, "lr": 5.143253690910419e-05, "epoch": 2.7039106145251397, "percentage": 54.18, "elapsed_time": "1:22:42", "remaining_time": "1:09:56"} {"current_steps": 364, "total_steps": 670, "loss": 0.0135, "lr": 5.117212868016303e-05, "epoch": 2.711359404096834, "percentage": 54.33, "elapsed_time": "1:22:55", "remaining_time": "1:09:42"} {"current_steps": 365, "total_steps": 670, "loss": 0.0147, "lr": 5.091168863567215e-05, "epoch": 2.718808193668529, "percentage": 54.48, "elapsed_time": "1:23:07", "remaining_time": "1:09:28"} {"current_steps": 365, "total_steps": 670, "eval_loss": 0.013487767428159714, "epoch": 2.718808193668529, "percentage": 54.48, "elapsed_time": "1:23:09", "remaining_time": "1:09:29"} {"current_steps": 366, "total_steps": 670, "loss": 0.018, "lr": 5.065122384485814e-05, "epoch": 2.7262569832402237, "percentage": 54.63, "elapsed_time": "1:23:22", "remaining_time": "1:09:15"} {"current_steps": 367, "total_steps": 670, "loss": 0.0149, "lr": 5.03907413776192e-05, "epoch": 2.733705772811918, "percentage": 54.78, "elapsed_time": "1:23:37", "remaining_time": "1:09:02"} {"current_steps": 368, "total_steps": 670, "loss": 0.0162, "lr": 5.013024830433338e-05, "epoch": 2.7411545623836124, "percentage": 54.93, "elapsed_time": "1:23:50", "remaining_time": "1:08:48"} {"current_steps": 369, "total_steps": 670, "loss": 0.0148, "lr": 4.9869751695666615e-05, "epoch": 2.7486033519553073, "percentage": 55.07, "elapsed_time": "1:24:03", "remaining_time": "1:08:34"} {"current_steps": 370, "total_steps": 670, "loss": 0.0127, "lr": 4.96092586223808e-05, "epoch": 2.756052141527002, "percentage": 55.22, "elapsed_time": "1:24:17", "remaining_time": "1:08:20"} {"current_steps": 370, "total_steps": 670, "eval_loss": 0.013425910845398903, "epoch": 2.756052141527002, "percentage": 55.22, "elapsed_time": "1:24:18", "remaining_time": "1:08:21"} {"current_steps": 371, "total_steps": 670, "loss": 0.0125, "lr": 4.9348776155141876e-05, "epoch": 2.7635009310986964, "percentage": 55.37, "elapsed_time": "1:24:32", "remaining_time": "1:08:07"} {"current_steps": 372, "total_steps": 670, "loss": 0.0151, "lr": 4.908831136432784e-05, "epoch": 2.770949720670391, "percentage": 55.52, "elapsed_time": "1:24:45", "remaining_time": "1:07:54"} {"current_steps": 373, "total_steps": 670, "loss": 0.0143, "lr": 4.882787131983698e-05, "epoch": 2.7783985102420856, "percentage": 55.67, "elapsed_time": "1:24:58", "remaining_time": "1:07:39"} {"current_steps": 374, "total_steps": 670, "loss": 0.014, "lr": 4.856746309089582e-05, "epoch": 2.7858472998137804, "percentage": 55.82, "elapsed_time": "1:25:12", "remaining_time": "1:07:26"} {"current_steps": 375, "total_steps": 670, "loss": 0.0144, "lr": 4.8307093745867335e-05, "epoch": 2.793296089385475, "percentage": 55.97, "elapsed_time": "1:25:27", "remaining_time": "1:07:13"} {"current_steps": 375, "total_steps": 670, "eval_loss": 0.013249891810119152, "epoch": 2.793296089385475, "percentage": 55.97, "elapsed_time": "1:25:28", "remaining_time": "1:07:14"} {"current_steps": 376, "total_steps": 670, "loss": 0.0122, "lr": 4.804677035205903e-05, "epoch": 2.8007448789571696, "percentage": 56.12, "elapsed_time": "1:25:43", "remaining_time": "1:07:01"} {"current_steps": 377, "total_steps": 670, "loss": 0.0136, "lr": 4.778649997553119e-05, "epoch": 2.808193668528864, "percentage": 56.27, "elapsed_time": "1:25:56", "remaining_time": "1:06:47"} {"current_steps": 378, "total_steps": 670, "loss": 0.0118, "lr": 4.752628968090496e-05, "epoch": 2.815642458100559, "percentage": 56.42, "elapsed_time": "1:26:09", "remaining_time": "1:06:33"} {"current_steps": 379, "total_steps": 670, "loss": 0.0113, "lr": 4.726614653117071e-05, "epoch": 2.823091247672253, "percentage": 56.57, "elapsed_time": "1:26:23", "remaining_time": "1:06:19"} {"current_steps": 380, "total_steps": 670, "loss": 0.0166, "lr": 4.700607758749625e-05, "epoch": 2.830540037243948, "percentage": 56.72, "elapsed_time": "1:26:36", "remaining_time": "1:06:05"} {"current_steps": 380, "total_steps": 670, "eval_loss": 0.013101673685014248, "epoch": 2.830540037243948, "percentage": 56.72, "elapsed_time": "1:26:37", "remaining_time": "1:06:06"} {"current_steps": 381, "total_steps": 670, "loss": 0.0133, "lr": 4.674608990903521e-05, "epoch": 2.8379888268156424, "percentage": 56.87, "elapsed_time": "1:26:51", "remaining_time": "1:05:53"} {"current_steps": 382, "total_steps": 670, "loss": 0.0133, "lr": 4.648619055273537e-05, "epoch": 2.845437616387337, "percentage": 57.01, "elapsed_time": "1:27:06", "remaining_time": "1:05:40"} {"current_steps": 383, "total_steps": 670, "loss": 0.0145, "lr": 4.622638657314716e-05, "epoch": 2.8528864059590315, "percentage": 57.16, "elapsed_time": "1:27:19", "remaining_time": "1:05:26"} {"current_steps": 384, "total_steps": 670, "loss": 0.0181, "lr": 4.596668502223214e-05, "epoch": 2.8603351955307263, "percentage": 57.31, "elapsed_time": "1:27:33", "remaining_time": "1:05:12"} {"current_steps": 385, "total_steps": 670, "loss": 0.0136, "lr": 4.5707092949171697e-05, "epoch": 2.8677839851024207, "percentage": 57.46, "elapsed_time": "1:27:46", "remaining_time": "1:04:58"} {"current_steps": 385, "total_steps": 670, "eval_loss": 0.01312539167702198, "epoch": 2.8677839851024207, "percentage": 57.46, "elapsed_time": "1:27:47", "remaining_time": "1:04:59"} {"current_steps": 386, "total_steps": 670, "loss": 0.0166, "lr": 4.544761740017553e-05, "epoch": 2.8752327746741155, "percentage": 57.61, "elapsed_time": "1:28:00", "remaining_time": "1:04:45"} {"current_steps": 387, "total_steps": 670, "loss": 0.0179, "lr": 4.518826541829049e-05, "epoch": 2.88268156424581, "percentage": 57.76, "elapsed_time": "1:28:14", "remaining_time": "1:04:31"} {"current_steps": 388, "total_steps": 670, "loss": 0.0185, "lr": 4.492904404320942e-05, "epoch": 2.8901303538175047, "percentage": 57.91, "elapsed_time": "1:28:28", "remaining_time": "1:04:18"} {"current_steps": 389, "total_steps": 670, "loss": 0.012, "lr": 4.466996031108004e-05, "epoch": 2.8975791433891995, "percentage": 58.06, "elapsed_time": "1:28:40", "remaining_time": "1:04:03"} {"current_steps": 390, "total_steps": 670, "loss": 0.0158, "lr": 4.441102125431398e-05, "epoch": 2.905027932960894, "percentage": 58.21, "elapsed_time": "1:28:52", "remaining_time": "1:03:48"} {"current_steps": 390, "total_steps": 670, "eval_loss": 0.01319090835750103, "epoch": 2.905027932960894, "percentage": 58.21, "elapsed_time": "1:28:54", "remaining_time": "1:03:49"} {"current_steps": 391, "total_steps": 670, "loss": 0.013, "lr": 4.415223390139588e-05, "epoch": 2.9124767225325883, "percentage": 58.36, "elapsed_time": "1:29:06", "remaining_time": "1:03:35"} {"current_steps": 392, "total_steps": 670, "loss": 0.0131, "lr": 4.3893605276692646e-05, "epoch": 2.919925512104283, "percentage": 58.51, "elapsed_time": "1:29:19", "remaining_time": "1:03:20"} {"current_steps": 393, "total_steps": 670, "loss": 0.0167, "lr": 4.3635142400262715e-05, "epoch": 2.927374301675978, "percentage": 58.66, "elapsed_time": "1:29:33", "remaining_time": "1:03:07"} {"current_steps": 394, "total_steps": 670, "loss": 0.0159, "lr": 4.3376852287665606e-05, "epoch": 2.9348230912476723, "percentage": 58.81, "elapsed_time": "1:29:47", "remaining_time": "1:02:54"} {"current_steps": 395, "total_steps": 670, "loss": 0.0118, "lr": 4.311874194977141e-05, "epoch": 2.9422718808193666, "percentage": 58.96, "elapsed_time": "1:30:00", "remaining_time": "1:02:40"} {"current_steps": 395, "total_steps": 670, "eval_loss": 0.013051866553723812, "epoch": 2.9422718808193666, "percentage": 58.96, "elapsed_time": "1:30:02", "remaining_time": "1:02:41"} {"current_steps": 396, "total_steps": 670, "loss": 0.0139, "lr": 4.2860818392570535e-05, "epoch": 2.9497206703910615, "percentage": 59.1, "elapsed_time": "1:30:15", "remaining_time": "1:02:26"} {"current_steps": 397, "total_steps": 670, "loss": 0.0137, "lr": 4.260308861698351e-05, "epoch": 2.9571694599627563, "percentage": 59.25, "elapsed_time": "1:30:28", "remaining_time": "1:02:13"} {"current_steps": 398, "total_steps": 670, "loss": 0.0146, "lr": 4.234555961867099e-05, "epoch": 2.9646182495344506, "percentage": 59.4, "elapsed_time": "1:30:42", "remaining_time": "1:01:59"} {"current_steps": 399, "total_steps": 670, "loss": 0.0127, "lr": 4.208823838784386e-05, "epoch": 2.972067039106145, "percentage": 59.55, "elapsed_time": "1:30:56", "remaining_time": "1:01:46"} {"current_steps": 400, "total_steps": 670, "loss": 0.0133, "lr": 4.183113190907349e-05, "epoch": 2.97951582867784, "percentage": 59.7, "elapsed_time": "1:31:10", "remaining_time": "1:01:32"} {"current_steps": 400, "total_steps": 670, "eval_loss": 0.01295236125588417, "epoch": 2.97951582867784, "percentage": 59.7, "elapsed_time": "1:31:11", "remaining_time": "1:01:33"} {"current_steps": 401, "total_steps": 670, "loss": 0.0139, "lr": 4.157424716110212e-05, "epoch": 2.9869646182495346, "percentage": 59.85, "elapsed_time": "1:31:25", "remaining_time": "1:01:20"} {"current_steps": 402, "total_steps": 670, "loss": 0.012, "lr": 4.131759111665349e-05, "epoch": 2.994413407821229, "percentage": 60.0, "elapsed_time": "1:31:39", "remaining_time": "1:01:06"} {"current_steps": 403, "total_steps": 670, "loss": 0.0255, "lr": 4.106117074224354e-05, "epoch": 3.001862197392924, "percentage": 60.15, "elapsed_time": "1:31:52", "remaining_time": "1:00:52"} {"current_steps": 404, "total_steps": 670, "loss": 0.0111, "lr": 4.080499299799133e-05, "epoch": 3.009310986964618, "percentage": 60.3, "elapsed_time": "1:32:06", "remaining_time": "1:00:38"} {"current_steps": 405, "total_steps": 670, "loss": 0.0126, "lr": 4.0549064837430124e-05, "epoch": 3.016759776536313, "percentage": 60.45, "elapsed_time": "1:32:20", "remaining_time": "1:00:25"} {"current_steps": 405, "total_steps": 670, "eval_loss": 0.012816812843084335, "epoch": 3.016759776536313, "percentage": 60.45, "elapsed_time": "1:32:22", "remaining_time": "1:00:26"} {"current_steps": 406, "total_steps": 670, "loss": 0.0147, "lr": 4.029339320731862e-05, "epoch": 3.0242085661080074, "percentage": 60.6, "elapsed_time": "1:32:35", "remaining_time": "1:00:12"} {"current_steps": 407, "total_steps": 670, "loss": 0.012, "lr": 4.003798504745243e-05, "epoch": 3.031657355679702, "percentage": 60.75, "elapsed_time": "1:32:49", "remaining_time": "0:59:59"} {"current_steps": 408, "total_steps": 670, "loss": 0.0141, "lr": 3.978284729047567e-05, "epoch": 3.0391061452513966, "percentage": 60.9, "elapsed_time": "1:33:02", "remaining_time": "0:59:44"} {"current_steps": 409, "total_steps": 670, "loss": 0.0118, "lr": 3.952798686169279e-05, "epoch": 3.0465549348230914, "percentage": 61.04, "elapsed_time": "1:33:15", "remaining_time": "0:59:30"} {"current_steps": 410, "total_steps": 670, "loss": 0.0121, "lr": 3.9273410678880654e-05, "epoch": 3.0540037243947857, "percentage": 61.19, "elapsed_time": "1:33:29", "remaining_time": "0:59:17"} {"current_steps": 410, "total_steps": 670, "eval_loss": 0.01281411200761795, "epoch": 3.0540037243947857, "percentage": 61.19, "elapsed_time": "1:33:30", "remaining_time": "0:59:17"} {"current_steps": 411, "total_steps": 670, "loss": 0.0128, "lr": 3.901912565210071e-05, "epoch": 3.0614525139664805, "percentage": 61.34, "elapsed_time": "1:33:43", "remaining_time": "0:59:03"} {"current_steps": 412, "total_steps": 670, "loss": 0.0128, "lr": 3.876513868351142e-05, "epoch": 3.068901303538175, "percentage": 61.49, "elapsed_time": "1:33:56", "remaining_time": "0:58:49"} {"current_steps": 413, "total_steps": 670, "loss": 0.0121, "lr": 3.851145666718095e-05, "epoch": 3.0763500931098697, "percentage": 61.64, "elapsed_time": "1:34:09", "remaining_time": "0:58:35"} {"current_steps": 414, "total_steps": 670, "loss": 0.0144, "lr": 3.825808648890005e-05, "epoch": 3.083798882681564, "percentage": 61.79, "elapsed_time": "1:34:22", "remaining_time": "0:58:21"} {"current_steps": 415, "total_steps": 670, "loss": 0.0127, "lr": 3.8005035025995104e-05, "epoch": 3.091247672253259, "percentage": 61.94, "elapsed_time": "1:34:35", "remaining_time": "0:58:07"} {"current_steps": 415, "total_steps": 670, "eval_loss": 0.012843618169426918, "epoch": 3.091247672253259, "percentage": 61.94, "elapsed_time": "1:34:36", "remaining_time": "0:58:08"} {"current_steps": 416, "total_steps": 670, "loss": 0.0144, "lr": 3.775230914714149e-05, "epoch": 3.0986964618249533, "percentage": 62.09, "elapsed_time": "1:34:50", "remaining_time": "0:57:54"} {"current_steps": 417, "total_steps": 670, "loss": 0.013, "lr": 3.7499915712177094e-05, "epoch": 3.106145251396648, "percentage": 62.24, "elapsed_time": "1:35:04", "remaining_time": "0:57:40"} {"current_steps": 418, "total_steps": 670, "loss": 0.0127, "lr": 3.7247861571916185e-05, "epoch": 3.1135940409683425, "percentage": 62.39, "elapsed_time": "1:35:17", "remaining_time": "0:57:27"} {"current_steps": 419, "total_steps": 670, "loss": 0.0111, "lr": 3.699615356796342e-05, "epoch": 3.1210428305400373, "percentage": 62.54, "elapsed_time": "1:35:31", "remaining_time": "0:57:13"} {"current_steps": 420, "total_steps": 670, "loss": 0.0128, "lr": 3.674479853252813e-05, "epoch": 3.1284916201117317, "percentage": 62.69, "elapsed_time": "1:35:45", "remaining_time": "0:56:59"} {"current_steps": 420, "total_steps": 670, "eval_loss": 0.012745661661028862, "epoch": 3.1284916201117317, "percentage": 62.69, "elapsed_time": "1:35:46", "remaining_time": "0:57:00"} {"current_steps": 421, "total_steps": 670, "loss": 0.0115, "lr": 3.6493803288238896e-05, "epoch": 3.1359404096834265, "percentage": 62.84, "elapsed_time": "1:35:59", "remaining_time": "0:56:46"} {"current_steps": 422, "total_steps": 670, "loss": 0.0129, "lr": 3.624317464795834e-05, "epoch": 3.143389199255121, "percentage": 62.99, "elapsed_time": "1:36:13", "remaining_time": "0:56:32"} {"current_steps": 423, "total_steps": 670, "loss": 0.0128, "lr": 3.599291941459818e-05, "epoch": 3.1508379888268156, "percentage": 63.13, "elapsed_time": "1:36:26", "remaining_time": "0:56:18"} {"current_steps": 424, "total_steps": 670, "loss": 0.0136, "lr": 3.574304438093466e-05, "epoch": 3.1582867783985105, "percentage": 63.28, "elapsed_time": "1:36:39", "remaining_time": "0:56:04"} {"current_steps": 425, "total_steps": 670, "loss": 0.0121, "lr": 3.549355632942405e-05, "epoch": 3.165735567970205, "percentage": 63.43, "elapsed_time": "1:36:51", "remaining_time": "0:55:50"} {"current_steps": 425, "total_steps": 670, "eval_loss": 0.012695872224867344, "epoch": 3.165735567970205, "percentage": 63.43, "elapsed_time": "1:36:53", "remaining_time": "0:55:51"} {"current_steps": 426, "total_steps": 670, "loss": 0.0163, "lr": 3.5244462032018666e-05, "epoch": 3.1731843575418996, "percentage": 63.58, "elapsed_time": "1:37:06", "remaining_time": "0:55:37"} {"current_steps": 427, "total_steps": 670, "loss": 0.0137, "lr": 3.499576824998298e-05, "epoch": 3.180633147113594, "percentage": 63.73, "elapsed_time": "1:37:21", "remaining_time": "0:55:24"} {"current_steps": 428, "total_steps": 670, "loss": 0.014, "lr": 3.474748173371008e-05, "epoch": 3.188081936685289, "percentage": 63.88, "elapsed_time": "1:37:35", "remaining_time": "0:55:11"} {"current_steps": 429, "total_steps": 670, "loss": 0.0122, "lr": 3.4499609222538576e-05, "epoch": 3.195530726256983, "percentage": 64.03, "elapsed_time": "1:37:49", "remaining_time": "0:54:57"} {"current_steps": 430, "total_steps": 670, "loss": 0.0121, "lr": 3.425215744456948e-05, "epoch": 3.202979515828678, "percentage": 64.18, "elapsed_time": "1:38:03", "remaining_time": "0:54:43"} {"current_steps": 430, "total_steps": 670, "eval_loss": 0.012730235233902931, "epoch": 3.202979515828678, "percentage": 64.18, "elapsed_time": "1:38:04", "remaining_time": "0:54:44"} {"current_steps": 431, "total_steps": 670, "loss": 0.0124, "lr": 3.400513311648372e-05, "epoch": 3.2104283054003724, "percentage": 64.33, "elapsed_time": "1:38:19", "remaining_time": "0:54:31"} {"current_steps": 432, "total_steps": 670, "loss": 0.0114, "lr": 3.375854294335977e-05, "epoch": 3.217877094972067, "percentage": 64.48, "elapsed_time": "1:38:33", "remaining_time": "0:54:17"} {"current_steps": 433, "total_steps": 670, "loss": 0.0143, "lr": 3.3512393618491676e-05, "epoch": 3.2253258845437616, "percentage": 64.63, "elapsed_time": "1:38:47", "remaining_time": "0:54:04"} {"current_steps": 434, "total_steps": 670, "loss": 0.0176, "lr": 3.326669182320736e-05, "epoch": 3.2327746741154564, "percentage": 64.78, "elapsed_time": "1:39:01", "remaining_time": "0:53:50"} {"current_steps": 435, "total_steps": 670, "loss": 0.0141, "lr": 3.302144422668726e-05, "epoch": 3.2402234636871508, "percentage": 64.93, "elapsed_time": "1:39:14", "remaining_time": "0:53:36"} {"current_steps": 435, "total_steps": 670, "eval_loss": 0.012653632089495659, "epoch": 3.2402234636871508, "percentage": 64.93, "elapsed_time": "1:39:15", "remaining_time": "0:53:37"} {"current_steps": 436, "total_steps": 670, "loss": 0.0129, "lr": 3.277665748578336e-05, "epoch": 3.2476722532588456, "percentage": 65.07, "elapsed_time": "1:39:28", "remaining_time": "0:53:23"} {"current_steps": 437, "total_steps": 670, "loss": 0.0123, "lr": 3.2532338244838415e-05, "epoch": 3.25512104283054, "percentage": 65.22, "elapsed_time": "1:39:42", "remaining_time": "0:53:09"} {"current_steps": 438, "total_steps": 670, "loss": 0.0168, "lr": 3.228849313550566e-05, "epoch": 3.2625698324022347, "percentage": 65.37, "elapsed_time": "1:39:55", "remaining_time": "0:52:55"} {"current_steps": 439, "total_steps": 670, "loss": 0.0124, "lr": 3.2045128776568784e-05, "epoch": 3.270018621973929, "percentage": 65.52, "elapsed_time": "1:40:08", "remaining_time": "0:52:41"} {"current_steps": 440, "total_steps": 670, "loss": 0.013, "lr": 3.180225177376229e-05, "epoch": 3.277467411545624, "percentage": 65.67, "elapsed_time": "1:40:21", "remaining_time": "0:52:27"} {"current_steps": 440, "total_steps": 670, "eval_loss": 0.012629649601876736, "epoch": 3.277467411545624, "percentage": 65.67, "elapsed_time": "1:40:23", "remaining_time": "0:52:28"} {"current_steps": 441, "total_steps": 670, "loss": 0.0147, "lr": 3.155986871959219e-05, "epoch": 3.2849162011173183, "percentage": 65.82, "elapsed_time": "1:40:35", "remaining_time": "0:52:14"} {"current_steps": 442, "total_steps": 670, "loss": 0.0114, "lr": 3.131798619315702e-05, "epoch": 3.292364990689013, "percentage": 65.97, "elapsed_time": "1:40:49", "remaining_time": "0:52:00"} {"current_steps": 443, "total_steps": 670, "loss": 0.0116, "lr": 3.107661075996932e-05, "epoch": 3.2998137802607075, "percentage": 66.12, "elapsed_time": "1:41:01", "remaining_time": "0:51:46"} {"current_steps": 444, "total_steps": 670, "loss": 0.0155, "lr": 3.083574897177741e-05, "epoch": 3.3072625698324023, "percentage": 66.27, "elapsed_time": "1:41:14", "remaining_time": "0:51:31"} {"current_steps": 445, "total_steps": 670, "loss": 0.0123, "lr": 3.0595407366387504e-05, "epoch": 3.3147113594040967, "percentage": 66.42, "elapsed_time": "1:41:27", "remaining_time": "0:51:18"} {"current_steps": 445, "total_steps": 670, "eval_loss": 0.012525614351034164, "epoch": 3.3147113594040967, "percentage": 66.42, "elapsed_time": "1:41:29", "remaining_time": "0:51:18"} {"current_steps": 446, "total_steps": 670, "loss": 0.0184, "lr": 3.035559246748635e-05, "epoch": 3.3221601489757915, "percentage": 66.57, "elapsed_time": "1:41:42", "remaining_time": "0:51:04"} {"current_steps": 447, "total_steps": 670, "loss": 0.0141, "lr": 3.0116310784464008e-05, "epoch": 3.329608938547486, "percentage": 66.72, "elapsed_time": "1:41:55", "remaining_time": "0:50:50"} {"current_steps": 448, "total_steps": 670, "loss": 0.0137, "lr": 2.987756881223732e-05, "epoch": 3.3370577281191807, "percentage": 66.87, "elapsed_time": "1:42:08", "remaining_time": "0:50:36"} {"current_steps": 449, "total_steps": 670, "loss": 0.0128, "lr": 2.9639373031073525e-05, "epoch": 3.344506517690875, "percentage": 67.01, "elapsed_time": "1:42:21", "remaining_time": "0:50:22"} {"current_steps": 450, "total_steps": 670, "loss": 0.0153, "lr": 2.940172990641438e-05, "epoch": 3.35195530726257, "percentage": 67.16, "elapsed_time": "1:42:33", "remaining_time": "0:50:08"} {"current_steps": 450, "total_steps": 670, "eval_loss": 0.012558124959468842, "epoch": 3.35195530726257, "percentage": 67.16, "elapsed_time": "1:42:34", "remaining_time": "0:50:09"} {"current_steps": 451, "total_steps": 670, "loss": 0.0123, "lr": 2.916464588870067e-05, "epoch": 3.3594040968342647, "percentage": 67.31, "elapsed_time": "1:42:49", "remaining_time": "0:49:55"} {"current_steps": 452, "total_steps": 670, "loss": 0.0141, "lr": 2.8928127413197124e-05, "epoch": 3.366852886405959, "percentage": 67.46, "elapsed_time": "1:43:01", "remaining_time": "0:49:41"} {"current_steps": 453, "total_steps": 670, "loss": 0.0117, "lr": 2.869218089981772e-05, "epoch": 3.3743016759776534, "percentage": 67.61, "elapsed_time": "1:43:15", "remaining_time": "0:49:27"} {"current_steps": 454, "total_steps": 670, "loss": 0.0118, "lr": 2.8456812752951485e-05, "epoch": 3.381750465549348, "percentage": 67.76, "elapsed_time": "1:43:28", "remaining_time": "0:49:13"} {"current_steps": 455, "total_steps": 670, "loss": 0.0148, "lr": 2.8222029361288583e-05, "epoch": 3.389199255121043, "percentage": 67.91, "elapsed_time": "1:43:40", "remaining_time": "0:48:59"} {"current_steps": 455, "total_steps": 670, "eval_loss": 0.012599460780620575, "epoch": 3.389199255121043, "percentage": 67.91, "elapsed_time": "1:43:41", "remaining_time": "0:48:59"} {"current_steps": 456, "total_steps": 670, "loss": 0.0156, "lr": 2.7987837097646908e-05, "epoch": 3.3966480446927374, "percentage": 68.06, "elapsed_time": "1:43:55", "remaining_time": "0:48:46"} {"current_steps": 457, "total_steps": 670, "loss": 0.0141, "lr": 2.7754242318799174e-05, "epoch": 3.404096834264432, "percentage": 68.21, "elapsed_time": "1:44:07", "remaining_time": "0:48:31"} {"current_steps": 458, "total_steps": 670, "loss": 0.0118, "lr": 2.752125136530036e-05, "epoch": 3.4115456238361266, "percentage": 68.36, "elapsed_time": "1:44:20", "remaining_time": "0:48:17"} {"current_steps": 459, "total_steps": 670, "loss": 0.0143, "lr": 2.7288870561315527e-05, "epoch": 3.4189944134078214, "percentage": 68.51, "elapsed_time": "1:44:33", "remaining_time": "0:48:03"} {"current_steps": 460, "total_steps": 670, "loss": 0.0136, "lr": 2.7057106214448212e-05, "epoch": 3.4264432029795158, "percentage": 68.66, "elapsed_time": "1:44:46", "remaining_time": "0:47:50"} {"current_steps": 460, "total_steps": 670, "eval_loss": 0.012621353380382061, "epoch": 3.4264432029795158, "percentage": 68.66, "elapsed_time": "1:44:48", "remaining_time": "0:47:50"} {"current_steps": 461, "total_steps": 670, "loss": 0.0116, "lr": 2.6825964615569233e-05, "epoch": 3.4338919925512106, "percentage": 68.81, "elapsed_time": "1:45:02", "remaining_time": "0:47:37"} {"current_steps": 462, "total_steps": 670, "loss": 0.0133, "lr": 2.6595452038645897e-05, "epoch": 3.441340782122905, "percentage": 68.96, "elapsed_time": "1:45:15", "remaining_time": "0:47:23"} {"current_steps": 463, "total_steps": 670, "loss": 0.0133, "lr": 2.636557474057173e-05, "epoch": 3.4487895716945998, "percentage": 69.1, "elapsed_time": "1:45:29", "remaining_time": "0:47:09"} {"current_steps": 464, "total_steps": 670, "loss": 0.0119, "lr": 2.6136338960996666e-05, "epoch": 3.456238361266294, "percentage": 69.25, "elapsed_time": "1:45:41", "remaining_time": "0:46:55"} {"current_steps": 465, "total_steps": 670, "loss": 0.0175, "lr": 2.5907750922157552e-05, "epoch": 3.463687150837989, "percentage": 69.4, "elapsed_time": "1:45:55", "remaining_time": "0:46:41"} {"current_steps": 465, "total_steps": 670, "eval_loss": 0.012514859437942505, "epoch": 3.463687150837989, "percentage": 69.4, "elapsed_time": "1:45:56", "remaining_time": "0:46:42"} {"current_steps": 466, "total_steps": 670, "loss": 0.0123, "lr": 2.5679816828709458e-05, "epoch": 3.4711359404096833, "percentage": 69.55, "elapsed_time": "1:46:09", "remaining_time": "0:46:28"} {"current_steps": 467, "total_steps": 670, "loss": 0.0145, "lr": 2.5452542867557117e-05, "epoch": 3.478584729981378, "percentage": 69.7, "elapsed_time": "1:46:23", "remaining_time": "0:46:14"} {"current_steps": 468, "total_steps": 670, "loss": 0.0129, "lr": 2.5225935207687025e-05, "epoch": 3.4860335195530725, "percentage": 69.85, "elapsed_time": "1:46:36", "remaining_time": "0:46:00"} {"current_steps": 469, "total_steps": 670, "loss": 0.0118, "lr": 2.500000000000001e-05, "epoch": 3.4934823091247673, "percentage": 70.0, "elapsed_time": "1:46:49", "remaining_time": "0:45:46"} {"current_steps": 470, "total_steps": 670, "loss": 0.0143, "lr": 2.4774743377144265e-05, "epoch": 3.5009310986964617, "percentage": 70.15, "elapsed_time": "1:47:01", "remaining_time": "0:45:32"} {"current_steps": 470, "total_steps": 670, "eval_loss": 0.012483342550694942, "epoch": 3.5009310986964617, "percentage": 70.15, "elapsed_time": "1:47:03", "remaining_time": "0:45:33"} {"current_steps": 471, "total_steps": 670, "loss": 0.0126, "lr": 2.4550171453348887e-05, "epoch": 3.5083798882681565, "percentage": 70.3, "elapsed_time": "1:47:16", "remaining_time": "0:45:19"} {"current_steps": 472, "total_steps": 670, "loss": 0.0132, "lr": 2.4326290324257894e-05, "epoch": 3.515828677839851, "percentage": 70.45, "elapsed_time": "1:47:28", "remaining_time": "0:45:05"} {"current_steps": 473, "total_steps": 670, "loss": 0.0141, "lr": 2.410310606676485e-05, "epoch": 3.5232774674115457, "percentage": 70.6, "elapsed_time": "1:47:42", "remaining_time": "0:44:51"} {"current_steps": 474, "total_steps": 670, "loss": 0.0116, "lr": 2.3880624738847835e-05, "epoch": 3.5307262569832405, "percentage": 70.75, "elapsed_time": "1:47:57", "remaining_time": "0:44:38"} {"current_steps": 475, "total_steps": 670, "loss": 0.0116, "lr": 2.3658852379404973e-05, "epoch": 3.538175046554935, "percentage": 70.9, "elapsed_time": "1:48:10", "remaining_time": "0:44:24"} {"current_steps": 475, "total_steps": 670, "eval_loss": 0.012377255596220493, "epoch": 3.538175046554935, "percentage": 70.9, "elapsed_time": "1:48:11", "remaining_time": "0:44:25"} {"current_steps": 476, "total_steps": 670, "loss": 0.0098, "lr": 2.3437795008090656e-05, "epoch": 3.5456238361266292, "percentage": 71.04, "elapsed_time": "1:48:25", "remaining_time": "0:44:11"} {"current_steps": 477, "total_steps": 670, "loss": 0.0134, "lr": 2.3217458625152038e-05, "epoch": 3.553072625698324, "percentage": 71.19, "elapsed_time": "1:48:37", "remaining_time": "0:43:57"} {"current_steps": 478, "total_steps": 670, "loss": 0.0117, "lr": 2.2997849211266222e-05, "epoch": 3.560521415270019, "percentage": 71.34, "elapsed_time": "1:48:51", "remaining_time": "0:43:43"} {"current_steps": 479, "total_steps": 670, "loss": 0.0135, "lr": 2.2778972727377868e-05, "epoch": 3.5679702048417132, "percentage": 71.49, "elapsed_time": "1:49:05", "remaining_time": "0:43:29"} {"current_steps": 480, "total_steps": 670, "loss": 0.012, "lr": 2.256083511453747e-05, "epoch": 3.5754189944134076, "percentage": 71.64, "elapsed_time": "1:49:18", "remaining_time": "0:43:16"} {"current_steps": 480, "total_steps": 670, "eval_loss": 0.012339064851403236, "epoch": 3.5754189944134076, "percentage": 71.64, "elapsed_time": "1:49:20", "remaining_time": "0:43:16"} {"current_steps": 481, "total_steps": 670, "loss": 0.0104, "lr": 2.234344229374003e-05, "epoch": 3.5828677839851024, "percentage": 71.79, "elapsed_time": "1:49:33", "remaining_time": "0:43:02"} {"current_steps": 482, "total_steps": 670, "loss": 0.0142, "lr": 2.2126800165764378e-05, "epoch": 3.5903165735567972, "percentage": 71.94, "elapsed_time": "1:49:46", "remaining_time": "0:42:48"} {"current_steps": 483, "total_steps": 670, "loss": 0.0118, "lr": 2.191091461101298e-05, "epoch": 3.5977653631284916, "percentage": 72.09, "elapsed_time": "1:49:59", "remaining_time": "0:42:35"} {"current_steps": 484, "total_steps": 670, "loss": 0.0148, "lr": 2.1695791489352345e-05, "epoch": 3.605214152700186, "percentage": 72.24, "elapsed_time": "1:50:11", "remaining_time": "0:42:20"} {"current_steps": 485, "total_steps": 670, "loss": 0.0116, "lr": 2.1481436639953984e-05, "epoch": 3.612662942271881, "percentage": 72.39, "elapsed_time": "1:50:24", "remaining_time": "0:42:06"} {"current_steps": 485, "total_steps": 670, "eval_loss": 0.01239725761115551, "epoch": 3.612662942271881, "percentage": 72.39, "elapsed_time": "1:50:26", "remaining_time": "0:42:07"} {"current_steps": 486, "total_steps": 670, "loss": 0.0137, "lr": 2.126785588113584e-05, "epoch": 3.6201117318435756, "percentage": 72.54, "elapsed_time": "1:50:40", "remaining_time": "0:41:54"} {"current_steps": 487, "total_steps": 670, "loss": 0.0145, "lr": 2.1055055010204427e-05, "epoch": 3.62756052141527, "percentage": 72.69, "elapsed_time": "1:50:52", "remaining_time": "0:41:39"} {"current_steps": 488, "total_steps": 670, "loss": 0.0122, "lr": 2.0843039803297516e-05, "epoch": 3.635009310986965, "percentage": 72.84, "elapsed_time": "1:51:05", "remaining_time": "0:41:25"} {"current_steps": 489, "total_steps": 670, "loss": 0.0119, "lr": 2.0631816015227218e-05, "epoch": 3.642458100558659, "percentage": 72.99, "elapsed_time": "1:51:20", "remaining_time": "0:41:12"} {"current_steps": 490, "total_steps": 670, "loss": 0.0127, "lr": 2.042138937932388e-05, "epoch": 3.649906890130354, "percentage": 73.13, "elapsed_time": "1:51:34", "remaining_time": "0:40:59"} {"current_steps": 490, "total_steps": 670, "eval_loss": 0.012451410293579102, "epoch": 3.649906890130354, "percentage": 73.13, "elapsed_time": "1:51:35", "remaining_time": "0:40:59"} {"current_steps": 491, "total_steps": 670, "loss": 0.0131, "lr": 2.021176560728043e-05, "epoch": 3.6573556797020483, "percentage": 73.28, "elapsed_time": "1:51:49", "remaining_time": "0:40:45"} {"current_steps": 492, "total_steps": 670, "loss": 0.0117, "lr": 2.0002950388997345e-05, "epoch": 3.664804469273743, "percentage": 73.43, "elapsed_time": "1:52:02", "remaining_time": "0:40:32"} {"current_steps": 493, "total_steps": 670, "loss": 0.0115, "lr": 1.979494939242822e-05, "epoch": 3.6722532588454375, "percentage": 73.58, "elapsed_time": "1:52:15", "remaining_time": "0:40:18"} {"current_steps": 494, "total_steps": 670, "loss": 0.0111, "lr": 1.9587768263425886e-05, "epoch": 3.6797020484171323, "percentage": 73.73, "elapsed_time": "1:52:29", "remaining_time": "0:40:04"} {"current_steps": 495, "total_steps": 670, "loss": 0.0158, "lr": 1.9381412625589234e-05, "epoch": 3.6871508379888267, "percentage": 73.88, "elapsed_time": "1:52:42", "remaining_time": "0:39:50"} {"current_steps": 495, "total_steps": 670, "eval_loss": 0.01239157933741808, "epoch": 3.6871508379888267, "percentage": 73.88, "elapsed_time": "1:52:43", "remaining_time": "0:39:51"} {"current_steps": 496, "total_steps": 670, "loss": 0.0128, "lr": 1.917588808011045e-05, "epoch": 3.6945996275605215, "percentage": 74.03, "elapsed_time": "1:52:57", "remaining_time": "0:39:37"} {"current_steps": 497, "total_steps": 670, "loss": 0.0157, "lr": 1.897120020562311e-05, "epoch": 3.702048417132216, "percentage": 74.18, "elapsed_time": "1:53:09", "remaining_time": "0:39:23"} {"current_steps": 498, "total_steps": 670, "loss": 0.0129, "lr": 1.8767354558050693e-05, "epoch": 3.7094972067039107, "percentage": 74.33, "elapsed_time": "1:53:23", "remaining_time": "0:39:09"} {"current_steps": 499, "total_steps": 670, "loss": 0.0135, "lr": 1.8564356670455767e-05, "epoch": 3.716945996275605, "percentage": 74.48, "elapsed_time": "1:53:37", "remaining_time": "0:38:56"} {"current_steps": 500, "total_steps": 670, "loss": 0.0126, "lr": 1.8362212052889826e-05, "epoch": 3.7243947858473, "percentage": 74.63, "elapsed_time": "1:53:50", "remaining_time": "0:38:42"} {"current_steps": 500, "total_steps": 670, "eval_loss": 0.01244338508695364, "epoch": 3.7243947858473, "percentage": 74.63, "elapsed_time": "1:53:51", "remaining_time": "0:38:42"} {"current_steps": 501, "total_steps": 670, "loss": 0.0126, "lr": 1.8160926192243698e-05, "epoch": 3.7318435754189943, "percentage": 74.78, "elapsed_time": "1:54:06", "remaining_time": "0:38:29"} {"current_steps": 502, "total_steps": 670, "loss": 0.0121, "lr": 1.796050455209869e-05, "epoch": 3.739292364990689, "percentage": 74.93, "elapsed_time": "1:54:20", "remaining_time": "0:38:15"} {"current_steps": 503, "total_steps": 670, "loss": 0.0111, "lr": 1.7760952572578182e-05, "epoch": 3.7467411545623834, "percentage": 75.07, "elapsed_time": "1:54:33", "remaining_time": "0:38:02"} {"current_steps": 504, "total_steps": 670, "loss": 0.0157, "lr": 1.756227567020004e-05, "epoch": 3.7541899441340782, "percentage": 75.22, "elapsed_time": "1:54:47", "remaining_time": "0:37:48"} {"current_steps": 505, "total_steps": 670, "loss": 0.0138, "lr": 1.7364479237729526e-05, "epoch": 3.761638733705773, "percentage": 75.37, "elapsed_time": "1:55:01", "remaining_time": "0:37:34"} {"current_steps": 505, "total_steps": 670, "eval_loss": 0.012437724508345127, "epoch": 3.761638733705773, "percentage": 75.37, "elapsed_time": "1:55:02", "remaining_time": "0:37:35"} {"current_steps": 506, "total_steps": 670, "loss": 0.0113, "lr": 1.7167568644033005e-05, "epoch": 3.7690875232774674, "percentage": 75.52, "elapsed_time": "1:55:16", "remaining_time": "0:37:21"} {"current_steps": 507, "total_steps": 670, "loss": 0.0117, "lr": 1.697154923393216e-05, "epoch": 3.776536312849162, "percentage": 75.67, "elapsed_time": "1:55:30", "remaining_time": "0:37:08"} {"current_steps": 508, "total_steps": 670, "loss": 0.0126, "lr": 1.677642632805892e-05, "epoch": 3.7839851024208566, "percentage": 75.82, "elapsed_time": "1:55:43", "remaining_time": "0:36:54"} {"current_steps": 509, "total_steps": 670, "loss": 0.0153, "lr": 1.658220522271105e-05, "epoch": 3.7914338919925514, "percentage": 75.97, "elapsed_time": "1:55:57", "remaining_time": "0:36:40"} {"current_steps": 510, "total_steps": 670, "loss": 0.0135, "lr": 1.63888911897084e-05, "epoch": 3.798882681564246, "percentage": 76.12, "elapsed_time": "1:56:11", "remaining_time": "0:36:27"} {"current_steps": 510, "total_steps": 670, "eval_loss": 0.012419372797012329, "epoch": 3.798882681564246, "percentage": 76.12, "elapsed_time": "1:56:12", "remaining_time": "0:36:27"} {"current_steps": 511, "total_steps": 670, "loss": 0.0138, "lr": 1.6196489476249777e-05, "epoch": 3.80633147113594, "percentage": 76.27, "elapsed_time": "1:56:26", "remaining_time": "0:36:13"} {"current_steps": 512, "total_steps": 670, "loss": 0.0122, "lr": 1.6005005304770552e-05, "epoch": 3.813780260707635, "percentage": 76.42, "elapsed_time": "1:56:38", "remaining_time": "0:35:59"} {"current_steps": 513, "total_steps": 670, "loss": 0.013, "lr": 1.5814443872800906e-05, "epoch": 3.82122905027933, "percentage": 76.57, "elapsed_time": "1:56:51", "remaining_time": "0:35:45"} {"current_steps": 514, "total_steps": 670, "loss": 0.0115, "lr": 1.562481035282471e-05, "epoch": 3.828677839851024, "percentage": 76.72, "elapsed_time": "1:57:05", "remaining_time": "0:35:32"} {"current_steps": 515, "total_steps": 670, "loss": 0.0126, "lr": 1.5436109892139177e-05, "epoch": 3.8361266294227185, "percentage": 76.87, "elapsed_time": "1:57:18", "remaining_time": "0:35:18"} {"current_steps": 515, "total_steps": 670, "eval_loss": 0.012386905029416084, "epoch": 3.8361266294227185, "percentage": 76.87, "elapsed_time": "1:57:20", "remaining_time": "0:35:18"} {"current_steps": 516, "total_steps": 670, "loss": 0.0156, "lr": 1.5248347612715119e-05, "epoch": 3.8435754189944134, "percentage": 77.01, "elapsed_time": "1:57:33", "remaining_time": "0:35:04"} {"current_steps": 517, "total_steps": 670, "loss": 0.0125, "lr": 1.5061528611057918e-05, "epoch": 3.851024208566108, "percentage": 77.16, "elapsed_time": "1:57:46", "remaining_time": "0:34:51"} {"current_steps": 518, "total_steps": 670, "loss": 0.0136, "lr": 1.4875657958069212e-05, "epoch": 3.8584729981378025, "percentage": 77.31, "elapsed_time": "1:58:00", "remaining_time": "0:34:37"} {"current_steps": 519, "total_steps": 670, "loss": 0.0105, "lr": 1.4690740698909222e-05, "epoch": 3.8659217877094973, "percentage": 77.46, "elapsed_time": "1:58:14", "remaining_time": "0:34:24"} {"current_steps": 520, "total_steps": 670, "loss": 0.0138, "lr": 1.4506781852859835e-05, "epoch": 3.8733705772811917, "percentage": 77.61, "elapsed_time": "1:58:27", "remaining_time": "0:34:10"} {"current_steps": 520, "total_steps": 670, "eval_loss": 0.012321457266807556, "epoch": 3.8733705772811917, "percentage": 77.61, "elapsed_time": "1:58:29", "remaining_time": "0:34:10"} {"current_steps": 521, "total_steps": 670, "loss": 0.0138, "lr": 1.432378641318835e-05, "epoch": 3.8808193668528865, "percentage": 77.76, "elapsed_time": "1:58:42", "remaining_time": "0:33:57"} {"current_steps": 522, "total_steps": 670, "loss": 0.0125, "lr": 1.4141759347011952e-05, "epoch": 3.888268156424581, "percentage": 77.91, "elapsed_time": "1:58:55", "remaining_time": "0:33:42"} {"current_steps": 523, "total_steps": 670, "loss": 0.0128, "lr": 1.3960705595162876e-05, "epoch": 3.8957169459962757, "percentage": 78.06, "elapsed_time": "1:59:10", "remaining_time": "0:33:29"} {"current_steps": 524, "total_steps": 670, "loss": 0.0126, "lr": 1.3780630072054313e-05, "epoch": 3.90316573556797, "percentage": 78.21, "elapsed_time": "1:59:24", "remaining_time": "0:33:16"} {"current_steps": 525, "total_steps": 670, "loss": 0.0117, "lr": 1.3601537665547009e-05, "epoch": 3.910614525139665, "percentage": 78.36, "elapsed_time": "1:59:37", "remaining_time": "0:33:02"} {"current_steps": 525, "total_steps": 670, "eval_loss": 0.012303684838116169, "epoch": 3.910614525139665, "percentage": 78.36, "elapsed_time": "1:59:39", "remaining_time": "0:33:02"} {"current_steps": 526, "total_steps": 670, "loss": 0.0119, "lr": 1.3423433236816563e-05, "epoch": 3.9180633147113593, "percentage": 78.51, "elapsed_time": "1:59:52", "remaining_time": "0:32:48"} {"current_steps": 527, "total_steps": 670, "loss": 0.0118, "lr": 1.324632162022153e-05, "epoch": 3.925512104283054, "percentage": 78.66, "elapsed_time": "2:00:05", "remaining_time": "0:32:35"} {"current_steps": 528, "total_steps": 670, "loss": 0.0139, "lr": 1.307020762317217e-05, "epoch": 3.9329608938547485, "percentage": 78.81, "elapsed_time": "2:00:19", "remaining_time": "0:32:21"} {"current_steps": 529, "total_steps": 670, "loss": 0.0117, "lr": 1.289509602599996e-05, "epoch": 3.9404096834264433, "percentage": 78.96, "elapsed_time": "2:00:32", "remaining_time": "0:32:07"} {"current_steps": 530, "total_steps": 670, "loss": 0.0126, "lr": 1.272099158182785e-05, "epoch": 3.9478584729981376, "percentage": 79.1, "elapsed_time": "2:00:47", "remaining_time": "0:31:54"} {"current_steps": 530, "total_steps": 670, "eval_loss": 0.012273291125893593, "epoch": 3.9478584729981376, "percentage": 79.1, "elapsed_time": "2:00:49", "remaining_time": "0:31:54"} {"current_steps": 531, "total_steps": 670, "loss": 0.0133, "lr": 1.2547899016441222e-05, "epoch": 3.9553072625698324, "percentage": 79.25, "elapsed_time": "2:01:02", "remaining_time": "0:31:41"} {"current_steps": 532, "total_steps": 670, "loss": 0.0151, "lr": 1.2375823028159667e-05, "epoch": 3.9627560521415273, "percentage": 79.4, "elapsed_time": "2:01:16", "remaining_time": "0:31:27"} {"current_steps": 533, "total_steps": 670, "loss": 0.0128, "lr": 1.2204768287709395e-05, "epoch": 3.9702048417132216, "percentage": 79.55, "elapsed_time": "2:01:29", "remaining_time": "0:31:13"} {"current_steps": 534, "total_steps": 670, "loss": 0.0119, "lr": 1.203473943809651e-05, "epoch": 3.977653631284916, "percentage": 79.7, "elapsed_time": "2:01:43", "remaining_time": "0:31:00"} {"current_steps": 535, "total_steps": 670, "loss": 0.0132, "lr": 1.1865741094480909e-05, "epoch": 3.985102420856611, "percentage": 79.85, "elapsed_time": "2:01:56", "remaining_time": "0:30:46"} {"current_steps": 535, "total_steps": 670, "eval_loss": 0.012257407419383526, "epoch": 3.985102420856611, "percentage": 79.85, "elapsed_time": "2:01:57", "remaining_time": "0:30:46"} {"current_steps": 536, "total_steps": 670, "loss": 0.0113, "lr": 1.1697777844051105e-05, "epoch": 3.9925512104283056, "percentage": 80.0, "elapsed_time": "2:02:11", "remaining_time": "0:30:32"} {"current_steps": 537, "total_steps": 670, "loss": 0.0235, "lr": 1.1530854245899659e-05, "epoch": 4.0, "percentage": 80.15, "elapsed_time": "2:02:25", "remaining_time": "0:30:19"} {"current_steps": 538, "total_steps": 670, "loss": 0.0116, "lr": 1.1364974830899439e-05, "epoch": 4.007448789571694, "percentage": 80.3, "elapsed_time": "2:02:38", "remaining_time": "0:30:05"} {"current_steps": 539, "total_steps": 670, "loss": 0.0116, "lr": 1.1200144101580635e-05, "epoch": 4.01489757914339, "percentage": 80.45, "elapsed_time": "2:02:52", "remaining_time": "0:29:51"} {"current_steps": 540, "total_steps": 670, "loss": 0.013, "lr": 1.1036366532008552e-05, "epoch": 4.022346368715084, "percentage": 80.6, "elapsed_time": "2:03:05", "remaining_time": "0:29:38"} {"current_steps": 540, "total_steps": 670, "eval_loss": 0.012261366471648216, "epoch": 4.022346368715084, "percentage": 80.6, "elapsed_time": "2:03:07", "remaining_time": "0:29:38"} {"current_steps": 541, "total_steps": 670, "loss": 0.0127, "lr": 1.0873646567662165e-05, "epoch": 4.029795158286778, "percentage": 80.75, "elapsed_time": "2:03:20", "remaining_time": "0:29:24"} {"current_steps": 542, "total_steps": 670, "loss": 0.0128, "lr": 1.0711988625313468e-05, "epoch": 4.037243947858473, "percentage": 80.9, "elapsed_time": "2:03:35", "remaining_time": "0:29:11"} {"current_steps": 543, "total_steps": 670, "loss": 0.0153, "lr": 1.055139709290755e-05, "epoch": 4.044692737430168, "percentage": 81.04, "elapsed_time": "2:03:47", "remaining_time": "0:28:57"} {"current_steps": 544, "total_steps": 670, "loss": 0.0131, "lr": 1.0391876329443533e-05, "epoch": 4.052141527001862, "percentage": 81.19, "elapsed_time": "2:04:01", "remaining_time": "0:28:43"} {"current_steps": 545, "total_steps": 670, "loss": 0.0131, "lr": 1.0233430664856236e-05, "epoch": 4.059590316573557, "percentage": 81.34, "elapsed_time": "2:04:15", "remaining_time": "0:28:29"} {"current_steps": 545, "total_steps": 670, "eval_loss": 0.012210767716169357, "epoch": 4.059590316573557, "percentage": 81.34, "elapsed_time": "2:04:16", "remaining_time": "0:28:30"} {"current_steps": 546, "total_steps": 670, "loss": 0.013, "lr": 1.0076064399898627e-05, "epoch": 4.067039106145251, "percentage": 81.49, "elapsed_time": "2:04:29", "remaining_time": "0:28:16"} {"current_steps": 547, "total_steps": 670, "loss": 0.0134, "lr": 9.919781806025135e-06, "epoch": 4.074487895716946, "percentage": 81.64, "elapsed_time": "2:04:41", "remaining_time": "0:28:02"} {"current_steps": 548, "total_steps": 670, "loss": 0.014, "lr": 9.764587125275654e-06, "epoch": 4.081936685288641, "percentage": 81.79, "elapsed_time": "2:04:54", "remaining_time": "0:27:48"} {"current_steps": 549, "total_steps": 670, "loss": 0.011, "lr": 9.610484570160444e-06, "epoch": 4.089385474860335, "percentage": 81.94, "elapsed_time": "2:05:09", "remaining_time": "0:27:35"} {"current_steps": 550, "total_steps": 670, "loss": 0.0156, "lr": 9.45747832354575e-06, "epoch": 4.0968342644320295, "percentage": 82.09, "elapsed_time": "2:05:22", "remaining_time": "0:27:21"} {"current_steps": 550, "total_steps": 670, "eval_loss": 0.012222141027450562, "epoch": 4.0968342644320295, "percentage": 82.09, "elapsed_time": "2:05:23", "remaining_time": "0:27:21"} {"current_steps": 551, "total_steps": 670, "loss": 0.011, "lr": 9.305572538540296e-06, "epoch": 4.104283054003725, "percentage": 82.24, "elapsed_time": "2:05:38", "remaining_time": "0:27:08"} {"current_steps": 552, "total_steps": 670, "loss": 0.0148, "lr": 9.154771338382545e-06, "epoch": 4.111731843575419, "percentage": 82.39, "elapsed_time": "2:05:51", "remaining_time": "0:26:54"} {"current_steps": 553, "total_steps": 670, "loss": 0.0109, "lr": 9.005078816328771e-06, "epoch": 4.1191806331471135, "percentage": 82.54, "elapsed_time": "2:06:05", "remaining_time": "0:26:40"} {"current_steps": 554, "total_steps": 670, "loss": 0.0131, "lr": 8.856499035541971e-06, "epoch": 4.126629422718808, "percentage": 82.69, "elapsed_time": "2:06:17", "remaining_time": "0:26:26"} {"current_steps": 555, "total_steps": 670, "loss": 0.0129, "lr": 8.70903602898157e-06, "epoch": 4.134078212290503, "percentage": 82.84, "elapsed_time": "2:06:30", "remaining_time": "0:26:12"} {"current_steps": 555, "total_steps": 670, "eval_loss": 0.012219291180372238, "epoch": 4.134078212290503, "percentage": 82.84, "elapsed_time": "2:06:32", "remaining_time": "0:26:13"} {"current_steps": 556, "total_steps": 670, "loss": 0.0133, "lr": 8.562693799293931e-06, "epoch": 4.1415270018621975, "percentage": 82.99, "elapsed_time": "2:06:44", "remaining_time": "0:25:59"} {"current_steps": 557, "total_steps": 670, "loss": 0.0121, "lr": 8.417476318703744e-06, "epoch": 4.148975791433892, "percentage": 83.13, "elapsed_time": "2:06:57", "remaining_time": "0:25:45"} {"current_steps": 558, "total_steps": 670, "loss": 0.013, "lr": 8.2733875289062e-06, "epoch": 4.156424581005586, "percentage": 83.28, "elapsed_time": "2:07:10", "remaining_time": "0:25:31"} {"current_steps": 559, "total_steps": 670, "loss": 0.0094, "lr": 8.130431340959981e-06, "epoch": 4.1638733705772815, "percentage": 83.43, "elapsed_time": "2:07:23", "remaining_time": "0:25:17"} {"current_steps": 560, "total_steps": 670, "loss": 0.0128, "lr": 7.988611635181098e-06, "epoch": 4.171322160148976, "percentage": 83.58, "elapsed_time": "2:07:36", "remaining_time": "0:25:04"} {"current_steps": 560, "total_steps": 670, "eval_loss": 0.01215694285929203, "epoch": 4.171322160148976, "percentage": 83.58, "elapsed_time": "2:07:38", "remaining_time": "0:25:04"} {"current_steps": 561, "total_steps": 670, "loss": 0.0123, "lr": 7.847932261037627e-06, "epoch": 4.17877094972067, "percentage": 83.73, "elapsed_time": "2:07:51", "remaining_time": "0:24:50"} {"current_steps": 562, "total_steps": 670, "loss": 0.0113, "lr": 7.708397037045129e-06, "epoch": 4.186219739292365, "percentage": 83.88, "elapsed_time": "2:08:05", "remaining_time": "0:24:36"} {"current_steps": 563, "total_steps": 670, "loss": 0.0126, "lr": 7.570009750663054e-06, "epoch": 4.19366852886406, "percentage": 84.03, "elapsed_time": "2:08:19", "remaining_time": "0:24:23"} {"current_steps": 564, "total_steps": 670, "loss": 0.0119, "lr": 7.432774158191946e-06, "epoch": 4.201117318435754, "percentage": 84.18, "elapsed_time": "2:08:32", "remaining_time": "0:24:09"} {"current_steps": 565, "total_steps": 670, "loss": 0.0098, "lr": 7.296693984671465e-06, "epoch": 4.208566108007449, "percentage": 84.33, "elapsed_time": "2:08:46", "remaining_time": "0:23:55"} {"current_steps": 565, "total_steps": 670, "eval_loss": 0.012128871865570545, "epoch": 4.208566108007449, "percentage": 84.33, "elapsed_time": "2:08:47", "remaining_time": "0:23:56"} {"current_steps": 566, "total_steps": 670, "loss": 0.0124, "lr": 7.161772923779258e-06, "epoch": 4.216014897579143, "percentage": 84.48, "elapsed_time": "2:09:01", "remaining_time": "0:23:42"} {"current_steps": 567, "total_steps": 670, "loss": 0.013, "lr": 7.0280146377307395e-06, "epoch": 4.223463687150838, "percentage": 84.63, "elapsed_time": "2:09:14", "remaining_time": "0:23:28"} {"current_steps": 568, "total_steps": 670, "loss": 0.0114, "lr": 6.8954227571796815e-06, "epoch": 4.230912476722533, "percentage": 84.78, "elapsed_time": "2:09:27", "remaining_time": "0:23:14"} {"current_steps": 569, "total_steps": 670, "loss": 0.0107, "lr": 6.764000881119631e-06, "epoch": 4.238361266294227, "percentage": 84.93, "elapsed_time": "2:09:40", "remaining_time": "0:23:01"} {"current_steps": 570, "total_steps": 670, "loss": 0.0109, "lr": 6.6337525767862505e-06, "epoch": 4.245810055865922, "percentage": 85.07, "elapsed_time": "2:09:54", "remaining_time": "0:22:47"} {"current_steps": 570, "total_steps": 670, "eval_loss": 0.012148498557507992, "epoch": 4.245810055865922, "percentage": 85.07, "elapsed_time": "2:09:55", "remaining_time": "0:22:47"} {"current_steps": 571, "total_steps": 670, "loss": 0.0103, "lr": 6.50468137956049e-06, "epoch": 4.253258845437617, "percentage": 85.22, "elapsed_time": "2:10:08", "remaining_time": "0:22:33"} {"current_steps": 572, "total_steps": 670, "loss": 0.0121, "lr": 6.376790792872611e-06, "epoch": 4.260707635009311, "percentage": 85.37, "elapsed_time": "2:10:21", "remaining_time": "0:22:19"} {"current_steps": 573, "total_steps": 670, "loss": 0.0128, "lr": 6.2500842881071e-06, "epoch": 4.268156424581005, "percentage": 85.52, "elapsed_time": "2:10:34", "remaining_time": "0:22:06"} {"current_steps": 574, "total_steps": 670, "loss": 0.0098, "lr": 6.124565304508439e-06, "epoch": 4.275605214152701, "percentage": 85.67, "elapsed_time": "2:10:48", "remaining_time": "0:21:52"} {"current_steps": 575, "total_steps": 670, "loss": 0.0128, "lr": 6.000237249087776e-06, "epoch": 4.283054003724395, "percentage": 85.82, "elapsed_time": "2:11:01", "remaining_time": "0:21:38"} {"current_steps": 575, "total_steps": 670, "eval_loss": 0.012117579579353333, "epoch": 4.283054003724395, "percentage": 85.82, "elapsed_time": "2:11:02", "remaining_time": "0:21:39"} {"current_steps": 576, "total_steps": 670, "loss": 0.0106, "lr": 5.877103496530395e-06, "epoch": 4.290502793296089, "percentage": 85.97, "elapsed_time": "2:11:16", "remaining_time": "0:21:25"} {"current_steps": 577, "total_steps": 670, "loss": 0.0137, "lr": 5.755167389104166e-06, "epoch": 4.297951582867784, "percentage": 86.12, "elapsed_time": "2:11:28", "remaining_time": "0:21:11"} {"current_steps": 578, "total_steps": 670, "loss": 0.0106, "lr": 5.634432236568815e-06, "epoch": 4.305400372439479, "percentage": 86.27, "elapsed_time": "2:11:42", "remaining_time": "0:20:57"} {"current_steps": 579, "total_steps": 670, "loss": 0.0121, "lr": 5.514901316086057e-06, "epoch": 4.312849162011173, "percentage": 86.42, "elapsed_time": "2:11:56", "remaining_time": "0:20:44"} {"current_steps": 580, "total_steps": 670, "loss": 0.0116, "lr": 5.3965778721306755e-06, "epoch": 4.320297951582868, "percentage": 86.57, "elapsed_time": "2:12:10", "remaining_time": "0:20:30"} {"current_steps": 580, "total_steps": 670, "eval_loss": 0.012121634557843208, "epoch": 4.320297951582868, "percentage": 86.57, "elapsed_time": "2:12:11", "remaining_time": "0:20:30"} {"current_steps": 581, "total_steps": 670, "loss": 0.0133, "lr": 5.279465116402438e-06, "epoch": 4.327746741154562, "percentage": 86.72, "elapsed_time": "2:12:24", "remaining_time": "0:20:16"} {"current_steps": 582, "total_steps": 670, "loss": 0.0099, "lr": 5.163566227738936e-06, "epoch": 4.335195530726257, "percentage": 86.87, "elapsed_time": "2:12:37", "remaining_time": "0:20:03"} {"current_steps": 583, "total_steps": 670, "loss": 0.0129, "lr": 5.048884352029271e-06, "epoch": 4.342644320297952, "percentage": 87.01, "elapsed_time": "2:12:50", "remaining_time": "0:19:49"} {"current_steps": 584, "total_steps": 670, "loss": 0.0145, "lr": 4.935422602128697e-06, "epoch": 4.350093109869646, "percentage": 87.16, "elapsed_time": "2:13:03", "remaining_time": "0:19:35"} {"current_steps": 585, "total_steps": 670, "loss": 0.0126, "lr": 4.823184057774116e-06, "epoch": 4.35754189944134, "percentage": 87.31, "elapsed_time": "2:13:16", "remaining_time": "0:19:21"} {"current_steps": 585, "total_steps": 670, "eval_loss": 0.012105356901884079, "epoch": 4.35754189944134, "percentage": 87.31, "elapsed_time": "2:13:17", "remaining_time": "0:19:22"} {"current_steps": 586, "total_steps": 670, "loss": 0.0123, "lr": 4.712171765500484e-06, "epoch": 4.364990689013036, "percentage": 87.46, "elapsed_time": "2:13:30", "remaining_time": "0:19:08"} {"current_steps": 587, "total_steps": 670, "loss": 0.013, "lr": 4.602388738558078e-06, "epoch": 4.37243947858473, "percentage": 87.61, "elapsed_time": "2:13:43", "remaining_time": "0:18:54"} {"current_steps": 588, "total_steps": 670, "loss": 0.0143, "lr": 4.493837956830788e-06, "epoch": 4.379888268156424, "percentage": 87.76, "elapsed_time": "2:13:56", "remaining_time": "0:18:40"} {"current_steps": 589, "total_steps": 670, "loss": 0.0142, "lr": 4.386522366755169e-06, "epoch": 4.387337057728119, "percentage": 87.91, "elapsed_time": "2:14:10", "remaining_time": "0:18:27"} {"current_steps": 590, "total_steps": 670, "loss": 0.0118, "lr": 4.280444881240475e-06, "epoch": 4.394785847299814, "percentage": 88.06, "elapsed_time": "2:14:22", "remaining_time": "0:18:13"} {"current_steps": 590, "total_steps": 670, "eval_loss": 0.012073861435055733, "epoch": 4.394785847299814, "percentage": 88.06, "elapsed_time": "2:14:24", "remaining_time": "0:18:13"} {"current_steps": 591, "total_steps": 670, "loss": 0.0144, "lr": 4.175608379589624e-06, "epoch": 4.402234636871508, "percentage": 88.21, "elapsed_time": "2:14:38", "remaining_time": "0:17:59"} {"current_steps": 592, "total_steps": 670, "loss": 0.0118, "lr": 4.072015707421006e-06, "epoch": 4.409683426443203, "percentage": 88.36, "elapsed_time": "2:14:52", "remaining_time": "0:17:46"} {"current_steps": 593, "total_steps": 670, "loss": 0.0137, "lr": 3.969669676591259e-06, "epoch": 4.417132216014897, "percentage": 88.51, "elapsed_time": "2:15:05", "remaining_time": "0:17:32"} {"current_steps": 594, "total_steps": 670, "loss": 0.012, "lr": 3.868573065118936e-06, "epoch": 4.424581005586592, "percentage": 88.66, "elapsed_time": "2:15:19", "remaining_time": "0:17:18"} {"current_steps": 595, "total_steps": 670, "loss": 0.0136, "lr": 3.768728617109135e-06, "epoch": 4.432029795158287, "percentage": 88.81, "elapsed_time": "2:15:32", "remaining_time": "0:17:05"} {"current_steps": 595, "total_steps": 670, "eval_loss": 0.012059464119374752, "epoch": 4.432029795158287, "percentage": 88.81, "elapsed_time": "2:15:34", "remaining_time": "0:17:05"} {"current_steps": 596, "total_steps": 670, "loss": 0.0123, "lr": 3.670139042678955e-06, "epoch": 4.439478584729981, "percentage": 88.96, "elapsed_time": "2:15:47", "remaining_time": "0:16:51"} {"current_steps": 597, "total_steps": 670, "loss": 0.0108, "lr": 3.5728070178839943e-06, "epoch": 4.446927374301676, "percentage": 89.1, "elapsed_time": "2:16:00", "remaining_time": "0:16:37"} {"current_steps": 598, "total_steps": 670, "loss": 0.0118, "lr": 3.476735184645674e-06, "epoch": 4.454376163873371, "percentage": 89.25, "elapsed_time": "2:16:14", "remaining_time": "0:16:24"} {"current_steps": 599, "total_steps": 670, "loss": 0.0106, "lr": 3.381926150679543e-06, "epoch": 4.461824953445065, "percentage": 89.4, "elapsed_time": "2:16:26", "remaining_time": "0:16:10"} {"current_steps": 600, "total_steps": 670, "loss": 0.0122, "lr": 3.288382489424502e-06, "epoch": 4.4692737430167595, "percentage": 89.55, "elapsed_time": "2:16:39", "remaining_time": "0:15:56"} {"current_steps": 600, "total_steps": 670, "eval_loss": 0.012050243094563484, "epoch": 4.4692737430167595, "percentage": 89.55, "elapsed_time": "2:16:41", "remaining_time": "0:15:56"} {"current_steps": 601, "total_steps": 670, "loss": 0.0122, "lr": 3.196106739972926e-06, "epoch": 4.476722532588455, "percentage": 89.7, "elapsed_time": "2:16:56", "remaining_time": "0:15:43"} {"current_steps": 602, "total_steps": 670, "loss": 0.0153, "lr": 3.10510140700177e-06, "epoch": 4.484171322160149, "percentage": 89.85, "elapsed_time": "2:17:10", "remaining_time": "0:15:29"} {"current_steps": 603, "total_steps": 670, "loss": 0.0139, "lr": 3.0153689607045845e-06, "epoch": 4.4916201117318435, "percentage": 90.0, "elapsed_time": "2:17:23", "remaining_time": "0:15:15"} {"current_steps": 604, "total_steps": 670, "loss": 0.0131, "lr": 2.9269118367244385e-06, "epoch": 4.499068901303538, "percentage": 90.15, "elapsed_time": "2:17:36", "remaining_time": "0:15:02"} {"current_steps": 605, "total_steps": 670, "loss": 0.0142, "lr": 2.839732436087833e-06, "epoch": 4.506517690875233, "percentage": 90.3, "elapsed_time": "2:17:50", "remaining_time": "0:14:48"} {"current_steps": 605, "total_steps": 670, "eval_loss": 0.012017564848065376, "epoch": 4.506517690875233, "percentage": 90.3, "elapsed_time": "2:17:51", "remaining_time": "0:14:48"} {"current_steps": 606, "total_steps": 670, "loss": 0.0105, "lr": 2.7538331251395266e-06, "epoch": 4.5139664804469275, "percentage": 90.45, "elapsed_time": "2:18:04", "remaining_time": "0:14:34"} {"current_steps": 607, "total_steps": 670, "loss": 0.0127, "lr": 2.6692162354782944e-06, "epoch": 4.521415270018622, "percentage": 90.6, "elapsed_time": "2:18:17", "remaining_time": "0:14:21"} {"current_steps": 608, "total_steps": 670, "loss": 0.0112, "lr": 2.585884063893651e-06, "epoch": 4.528864059590316, "percentage": 90.75, "elapsed_time": "2:18:30", "remaining_time": "0:14:07"} {"current_steps": 609, "total_steps": 670, "loss": 0.0126, "lr": 2.5038388723034932e-06, "epoch": 4.5363128491620115, "percentage": 90.9, "elapsed_time": "2:18:43", "remaining_time": "0:13:53"} {"current_steps": 610, "total_steps": 670, "loss": 0.011, "lr": 2.4230828876927294e-06, "epoch": 4.543761638733706, "percentage": 91.04, "elapsed_time": "2:18:57", "remaining_time": "0:13:40"} {"current_steps": 610, "total_steps": 670, "eval_loss": 0.01203765906393528, "epoch": 4.543761638733706, "percentage": 91.04, "elapsed_time": "2:18:59", "remaining_time": "0:13:40"} {"current_steps": 611, "total_steps": 670, "loss": 0.0118, "lr": 2.343618302052808e-06, "epoch": 4.5512104283054, "percentage": 91.19, "elapsed_time": "2:19:12", "remaining_time": "0:13:26"} {"current_steps": 612, "total_steps": 670, "loss": 0.0134, "lr": 2.265447272322213e-06, "epoch": 4.558659217877095, "percentage": 91.34, "elapsed_time": "2:19:26", "remaining_time": "0:13:12"} {"current_steps": 613, "total_steps": 670, "loss": 0.0121, "lr": 2.1885719203279588e-06, "epoch": 4.56610800744879, "percentage": 91.49, "elapsed_time": "2:19:41", "remaining_time": "0:12:59"} {"current_steps": 614, "total_steps": 670, "loss": 0.0117, "lr": 2.112994332727952e-06, "epoch": 4.573556797020484, "percentage": 91.64, "elapsed_time": "2:19:54", "remaining_time": "0:12:45"} {"current_steps": 615, "total_steps": 670, "loss": 0.011, "lr": 2.0387165609543736e-06, "epoch": 4.581005586592179, "percentage": 91.79, "elapsed_time": "2:20:08", "remaining_time": "0:12:31"} {"current_steps": 615, "total_steps": 670, "eval_loss": 0.01203648466616869, "epoch": 4.581005586592179, "percentage": 91.79, "elapsed_time": "2:20:09", "remaining_time": "0:12:32"} {"current_steps": 616, "total_steps": 670, "loss": 0.0127, "lr": 1.9657406211579966e-06, "epoch": 4.588454376163874, "percentage": 91.94, "elapsed_time": "2:20:23", "remaining_time": "0:12:18"} {"current_steps": 617, "total_steps": 670, "loss": 0.0117, "lr": 1.8940684941534392e-06, "epoch": 4.595903165735568, "percentage": 92.09, "elapsed_time": "2:20:37", "remaining_time": "0:12:04"} {"current_steps": 618, "total_steps": 670, "loss": 0.0122, "lr": 1.8237021253654396e-06, "epoch": 4.603351955307263, "percentage": 92.24, "elapsed_time": "2:20:50", "remaining_time": "0:11:51"} {"current_steps": 619, "total_steps": 670, "loss": 0.0135, "lr": 1.7546434247760146e-06, "epoch": 4.610800744878957, "percentage": 92.39, "elapsed_time": "2:21:04", "remaining_time": "0:11:37"} {"current_steps": 620, "total_steps": 670, "loss": 0.011, "lr": 1.6868942668726407e-06, "epoch": 4.618249534450651, "percentage": 92.54, "elapsed_time": "2:21:17", "remaining_time": "0:11:23"} {"current_steps": 620, "total_steps": 670, "eval_loss": 0.01203606091439724, "epoch": 4.618249534450651, "percentage": 92.54, "elapsed_time": "2:21:19", "remaining_time": "0:11:23"} {"current_steps": 621, "total_steps": 670, "loss": 0.0118, "lr": 1.6204564905973386e-06, "epoch": 4.625698324022347, "percentage": 92.69, "elapsed_time": "2:21:32", "remaining_time": "0:11:10"} {"current_steps": 622, "total_steps": 670, "loss": 0.0154, "lr": 1.555331899296808e-06, "epoch": 4.633147113594041, "percentage": 92.84, "elapsed_time": "2:21:45", "remaining_time": "0:10:56"} {"current_steps": 623, "total_steps": 670, "loss": 0.0127, "lr": 1.4915222606734392e-06, "epoch": 4.640595903165735, "percentage": 92.99, "elapsed_time": "2:21:57", "remaining_time": "0:10:42"} {"current_steps": 624, "total_steps": 670, "loss": 0.0116, "lr": 1.429029306737345e-06, "epoch": 4.648044692737431, "percentage": 93.13, "elapsed_time": "2:22:11", "remaining_time": "0:10:28"} {"current_steps": 625, "total_steps": 670, "loss": 0.0104, "lr": 1.3678547337593494e-06, "epoch": 4.655493482309125, "percentage": 93.28, "elapsed_time": "2:22:25", "remaining_time": "0:10:15"} {"current_steps": 625, "total_steps": 670, "eval_loss": 0.012031874619424343, "epoch": 4.655493482309125, "percentage": 93.28, "elapsed_time": "2:22:26", "remaining_time": "0:10:15"} {"current_steps": 626, "total_steps": 670, "loss": 0.0149, "lr": 1.3080002022249405e-06, "epoch": 4.662942271880819, "percentage": 93.43, "elapsed_time": "2:22:39", "remaining_time": "0:10:01"} {"current_steps": 627, "total_steps": 670, "loss": 0.0107, "lr": 1.2494673367892062e-06, "epoch": 4.670391061452514, "percentage": 93.58, "elapsed_time": "2:22:52", "remaining_time": "0:09:47"} {"current_steps": 628, "total_steps": 670, "loss": 0.0112, "lr": 1.1922577262327373e-06, "epoch": 4.677839851024208, "percentage": 93.73, "elapsed_time": "2:23:05", "remaining_time": "0:09:34"} {"current_steps": 629, "total_steps": 670, "loss": 0.0141, "lr": 1.1363729234184827e-06, "epoch": 4.685288640595903, "percentage": 93.88, "elapsed_time": "2:23:19", "remaining_time": "0:09:20"} {"current_steps": 630, "total_steps": 670, "loss": 0.0113, "lr": 1.0818144452496292e-06, "epoch": 4.692737430167598, "percentage": 94.03, "elapsed_time": "2:23:33", "remaining_time": "0:09:06"} {"current_steps": 630, "total_steps": 670, "eval_loss": 0.012034347280859947, "epoch": 4.692737430167598, "percentage": 94.03, "elapsed_time": "2:23:34", "remaining_time": "0:09:06"} {"current_steps": 631, "total_steps": 670, "loss": 0.0126, "lr": 1.0285837726283998e-06, "epoch": 4.700186219739292, "percentage": 94.18, "elapsed_time": "2:23:48", "remaining_time": "0:08:53"} {"current_steps": 632, "total_steps": 670, "loss": 0.0123, "lr": 9.76682350415875e-07, "epoch": 4.707635009310987, "percentage": 94.33, "elapsed_time": "2:24:02", "remaining_time": "0:08:39"} {"current_steps": 633, "total_steps": 670, "loss": 0.0139, "lr": 9.261115873927695e-07, "epoch": 4.715083798882682, "percentage": 94.48, "elapsed_time": "2:24:14", "remaining_time": "0:08:25"} {"current_steps": 634, "total_steps": 670, "loss": 0.0116, "lr": 8.768728562211947e-07, "epoch": 4.722532588454376, "percentage": 94.63, "elapsed_time": "2:24:28", "remaining_time": "0:08:12"} {"current_steps": 635, "total_steps": 670, "loss": 0.0123, "lr": 8.289674934073844e-07, "epoch": 4.72998137802607, "percentage": 94.78, "elapsed_time": "2:24:41", "remaining_time": "0:07:58"} {"current_steps": 635, "total_steps": 670, "eval_loss": 0.011995038017630577, "epoch": 4.72998137802607, "percentage": 94.78, "elapsed_time": "2:24:43", "remaining_time": "0:07:58"} {"current_steps": 636, "total_steps": 670, "loss": 0.0118, "lr": 7.823967992654502e-07, "epoch": 4.737430167597766, "percentage": 94.93, "elapsed_time": "2:24:56", "remaining_time": "0:07:44"} {"current_steps": 637, "total_steps": 670, "loss": 0.0128, "lr": 7.371620378820554e-07, "epoch": 4.74487895716946, "percentage": 95.07, "elapsed_time": "2:25:10", "remaining_time": "0:07:31"} {"current_steps": 638, "total_steps": 670, "loss": 0.0133, "lr": 6.932644370821085e-07, "epoch": 4.752327746741154, "percentage": 95.22, "elapsed_time": "2:25:23", "remaining_time": "0:07:17"} {"current_steps": 639, "total_steps": 670, "loss": 0.0117, "lr": 6.507051883954618e-07, "epoch": 4.759776536312849, "percentage": 95.37, "elapsed_time": "2:25:36", "remaining_time": "0:07:03"} {"current_steps": 640, "total_steps": 670, "loss": 0.011, "lr": 6.094854470245326e-07, "epoch": 4.767225325884544, "percentage": 95.52, "elapsed_time": "2:25:50", "remaining_time": "0:06:50"} {"current_steps": 640, "total_steps": 670, "eval_loss": 0.012030351907014847, "epoch": 4.767225325884544, "percentage": 95.52, "elapsed_time": "2:25:52", "remaining_time": "0:06:50"} {"current_steps": 641, "total_steps": 670, "loss": 0.0117, "lr": 5.696063318129663e-07, "epoch": 4.774674115456238, "percentage": 95.67, "elapsed_time": "2:26:04", "remaining_time": "0:06:36"} {"current_steps": 642, "total_steps": 670, "loss": 0.0121, "lr": 5.310689252152834e-07, "epoch": 4.782122905027933, "percentage": 95.82, "elapsed_time": "2:26:17", "remaining_time": "0:06:22"} {"current_steps": 643, "total_steps": 670, "loss": 0.0123, "lr": 4.938742732674529e-07, "epoch": 4.789571694599628, "percentage": 95.97, "elapsed_time": "2:26:30", "remaining_time": "0:06:09"} {"current_steps": 644, "total_steps": 670, "loss": 0.0158, "lr": 4.5802338555854254e-07, "epoch": 4.797020484171322, "percentage": 96.12, "elapsed_time": "2:26:44", "remaining_time": "0:05:55"} {"current_steps": 645, "total_steps": 670, "loss": 0.0125, "lr": 4.235172352033023e-07, "epoch": 4.804469273743017, "percentage": 96.27, "elapsed_time": "2:26:57", "remaining_time": "0:05:41"} {"current_steps": 645, "total_steps": 670, "eval_loss": 0.012008597142994404, "epoch": 4.804469273743017, "percentage": 96.27, "elapsed_time": "2:26:58", "remaining_time": "0:05:41"} {"current_steps": 646, "total_steps": 670, "loss": 0.0106, "lr": 3.903567588157353e-07, "epoch": 4.811918063314711, "percentage": 96.42, "elapsed_time": "2:27:11", "remaining_time": "0:05:28"} {"current_steps": 647, "total_steps": 670, "loss": 0.0123, "lr": 3.585428564836957e-07, "epoch": 4.8193668528864055, "percentage": 96.57, "elapsed_time": "2:27:25", "remaining_time": "0:05:14"} {"current_steps": 648, "total_steps": 670, "loss": 0.0131, "lr": 3.280763917444363e-07, "epoch": 4.826815642458101, "percentage": 96.72, "elapsed_time": "2:27:40", "remaining_time": "0:05:00"} {"current_steps": 649, "total_steps": 670, "loss": 0.0108, "lr": 2.9895819156119943e-07, "epoch": 4.834264432029795, "percentage": 96.87, "elapsed_time": "2:27:52", "remaining_time": "0:04:47"} {"current_steps": 650, "total_steps": 670, "loss": 0.0121, "lr": 2.711890463007405e-07, "epoch": 4.8417132216014895, "percentage": 97.01, "elapsed_time": "2:28:06", "remaining_time": "0:04:33"} {"current_steps": 650, "total_steps": 670, "eval_loss": 0.012026778422296047, "epoch": 4.8417132216014895, "percentage": 97.01, "elapsed_time": "2:28:07", "remaining_time": "0:04:33"} {"current_steps": 651, "total_steps": 670, "loss": 0.0117, "lr": 2.447697097118951e-07, "epoch": 4.849162011173185, "percentage": 97.16, "elapsed_time": "2:28:21", "remaining_time": "0:04:19"} {"current_steps": 652, "total_steps": 670, "loss": 0.0126, "lr": 2.1970089890509527e-07, "epoch": 4.856610800744879, "percentage": 97.31, "elapsed_time": "2:28:36", "remaining_time": "0:04:06"} {"current_steps": 653, "total_steps": 670, "loss": 0.0115, "lr": 1.9598329433293538e-07, "epoch": 4.8640595903165735, "percentage": 97.46, "elapsed_time": "2:28:49", "remaining_time": "0:03:52"} {"current_steps": 654, "total_steps": 670, "loss": 0.014, "lr": 1.7361753977169215e-07, "epoch": 4.871508379888268, "percentage": 97.61, "elapsed_time": "2:29:01", "remaining_time": "0:03:38"} {"current_steps": 655, "total_steps": 670, "loss": 0.0124, "lr": 1.5260424230382763e-07, "epoch": 4.878957169459962, "percentage": 97.76, "elapsed_time": "2:29:15", "remaining_time": "0:03:25"} {"current_steps": 655, "total_steps": 670, "eval_loss": 0.01201613713055849, "epoch": 4.878957169459962, "percentage": 97.76, "elapsed_time": "2:29:16", "remaining_time": "0:03:25"} {"current_steps": 656, "total_steps": 670, "loss": 0.016, "lr": 1.3294397230153577e-07, "epoch": 4.8864059590316575, "percentage": 97.91, "elapsed_time": "2:29:29", "remaining_time": "0:03:11"} {"current_steps": 657, "total_steps": 670, "loss": 0.0113, "lr": 1.1463726341126025e-07, "epoch": 4.893854748603352, "percentage": 98.06, "elapsed_time": "2:29:43", "remaining_time": "0:02:57"} {"current_steps": 658, "total_steps": 670, "loss": 0.0124, "lr": 9.768461253920614e-08, "epoch": 4.901303538175046, "percentage": 98.21, "elapsed_time": "2:29:57", "remaining_time": "0:02:44"} {"current_steps": 659, "total_steps": 670, "loss": 0.0112, "lr": 8.208647983782847e-08, "epoch": 4.9087523277467415, "percentage": 98.36, "elapsed_time": "2:30:10", "remaining_time": "0:02:30"} {"current_steps": 660, "total_steps": 670, "loss": 0.0102, "lr": 6.784328869339218e-08, "epoch": 4.916201117318436, "percentage": 98.51, "elapsed_time": "2:30:23", "remaining_time": "0:02:16"} {"current_steps": 660, "total_steps": 670, "eval_loss": 0.012047892436385155, "epoch": 4.916201117318436, "percentage": 98.51, "elapsed_time": "2:30:25", "remaining_time": "0:02:16"} {"current_steps": 661, "total_steps": 670, "loss": 0.0135, "lr": 5.4955425714431353e-08, "epoch": 4.92364990689013, "percentage": 98.66, "elapsed_time": "2:30:38", "remaining_time": "0:02:03"} {"current_steps": 662, "total_steps": 670, "loss": 0.0123, "lr": 4.3423240721268686e-08, "epoch": 4.931098696461825, "percentage": 98.81, "elapsed_time": "2:30:52", "remaining_time": "0:01:49"} {"current_steps": 663, "total_steps": 670, "loss": 0.0121, "lr": 3.324704673655088e-08, "epoch": 4.93854748603352, "percentage": 98.96, "elapsed_time": "2:31:06", "remaining_time": "0:01:35"} {"current_steps": 664, "total_steps": 670, "loss": 0.0121, "lr": 2.442711997670544e-08, "epoch": 4.945996275605214, "percentage": 99.1, "elapsed_time": "2:31:19", "remaining_time": "0:01:22"} {"current_steps": 665, "total_steps": 670, "loss": 0.0151, "lr": 1.6963699844474434e-08, "epoch": 4.953445065176909, "percentage": 99.25, "elapsed_time": "2:31:32", "remaining_time": "0:01:08"} {"current_steps": 665, "total_steps": 670, "eval_loss": 0.012051703408360481, "epoch": 4.953445065176909, "percentage": 99.25, "elapsed_time": "2:31:33", "remaining_time": "0:01:08"} {"current_steps": 666, "total_steps": 670, "loss": 0.0123, "lr": 1.0856988922403056e-08, "epoch": 4.960893854748603, "percentage": 99.4, "elapsed_time": "2:31:47", "remaining_time": "0:00:54"} {"current_steps": 667, "total_steps": 670, "loss": 0.0116, "lr": 6.107152967349539e-09, "epoch": 4.968342644320298, "percentage": 99.55, "elapsed_time": "2:32:00", "remaining_time": "0:00:41"} {"current_steps": 668, "total_steps": 670, "loss": 0.0153, "lr": 2.714320905977674e-09, "epoch": 4.975791433891993, "percentage": 99.7, "elapsed_time": "2:32:13", "remaining_time": "0:00:27"} {"current_steps": 669, "total_steps": 670, "loss": 0.014, "lr": 6.785848312707011e-10, "epoch": 4.983240223463687, "percentage": 99.85, "elapsed_time": "2:32:26", "remaining_time": "0:00:13"} {"current_steps": 670, "total_steps": 670, "loss": 0.0125, "lr": 0.0, "epoch": 4.990689013035381, "percentage": 100.0, "elapsed_time": "2:32:39", "remaining_time": "0:00:00"} {"current_steps": 670, "total_steps": 670, "eval_loss": 0.012047401629388332, "epoch": 4.990689013035381, "percentage": 100.0, "elapsed_time": "2:32:40", "remaining_time": "0:00:00"} {"current_steps": 670, "total_steps": 670, "epoch": 4.990689013035381, "percentage": 100.0, "elapsed_time": "2:32:41", "remaining_time": "0:00:00"}